International Association
for Cryptologic Research

Masking stands as one of the most effective countermeasures against side-channel attacks. While a number of recent works have investigated first-order masking schemes that eliminate the need for fresh randomness, most existing solutions trade off this randomness reduction against increased latency or area overhead. This paper targets the simultaneous achievement of low latency and zero fresh randomness. To this end, we make the following contributions. First, we identify a security flaw in the round-based design proposed by Askeland et al.\ at CARDIS 2022, which builds upon the Changing of the Guards (COTG) technique. Second, we propose a revised construction that rectifies this vulnerability without incurring any additional randomness or latency penalty. Finally, by integrating the Time Sharing Masking (TSM) S-box introduced at CHES 2025, we present a first-order masked AES implementation with a latency of 20 clock cycles that requires no fresh randomness.

The eSIM specification enables remote SIM provisioning without the need to hand out a physical SIM card. Instead of a physical SIM card, the subscriber downloads a SIM profile, which contains a subscriber's identity and authentication key material, to their embedded UICC, a discrete, embedded chip in the user's phone. This provisioning process is specified in the remote SIM provisioning (RSP) protocol and is secured through contemporary public-key cryptography. However, the potential advent of general-purpose quantum computers threatens the security of RSP.

This paper provides a quantum threat analysis of the RSP protocol, considering both Harvest Now, Decrypt Later attacks and active quantum attacks. To alleviate this threat, this paper introduces PQC-RSP, a post quantum secure version of the RSP protocol. The main challenge we address is the introduction of key encapsulation mechanisms (KEMs) into the RSP protocol, both in a PQC-only and hybrid version, and the security implications of this modification. We prove the security of PQC-RSP and review the performance overhead introduced through the usage of post quantum cryptography.

We initiate the study of \emph{arithmetic} private information retrieval (APIR) schemes, in which the database is a vector of field elements and the scheme makes a black-box use of the field. We obtain the following results.

\begin{itemize} \item Our main result is a negative one: We show that no single-server APIR scheme can achieve non-trivial download cost smaller than $n$ field elements. We observe that recent proposals for code-based PIR (Holzbaur et al., ISIT'20; Verma and Hollanti, ISIT'24) are arithmetic, and show how to break them within a few minutes on a standard workstation for all suggested parameters.

\item We complement the above by positive results in alternative models. Concretely, we show that with either two servers or a single server with secret-key preprocessing, it is possible to construct computationally secure APIR schemes based on well-studied coding assumptions. This is achieved by arithmetizing the distributed-point-function-based PIR of Boyle et al.~(CCS'16), and by observing that the recent construction of secret-key single-server PIR by Chen et al.~(STOC'26) also arithmetizes.

\item Finally, we characterize the existence of information-theoretic two-server APIR schemes in linear-algebraic terms, and show that communication of $O(n^{1/3})$ can be achieved in this setting based on the original approach of Chor et al.~(FOCS'95). The optimality of this result remains an interesting open question. \end{itemize}

This document provides a machine-checked Isabelle/HOL formalisation of the modular-arithmetic core of the Neon NTT paper of Becker, Hwang, Kannwischer, Yang, and Yang. We develop parametric theories of Barrett and Montgomery reduction and multiplication; the equivalence of Barrett and Montgomery arithmetic; the doubling- and rounding-Montgomery variants; and correctness and bounds theorems for Neon assembly kernels, against a hand-written model of the word arithmetic underlying the relevant Neon instructions. The development is a directed auto-formalisation: definitions, theorem statements, and proofs were produced by Claude Opus 4.7 and 4.8 using AutoCorrode's LLM-Isabelle integration layers. The human author set the architecture, chose abstractions and proof strategies, often nudged the model toward shorter or cleaner proofs, and controlled which output entered the development. This document is auto-generated from the Isabelle sources through Isabelle’s document preparation system, eliminating drift between prose and formal artifact.

Emerging attacks and applications have motivated the development of transforms that turn a given AE scheme into a committing AE (cAE) one. We give a new transform called UCX with the following attributes: It does not require the starting scheme to be tag based, works for schemes in the broad AE5 framework rather than the limited AE1 one, and preserves both UNAE (Unique Nonce AE) and MRAE (Misuse Resistant AE) security. No prior transform is ``universal'' in the sense of having the combination of all these properties. The use of UCX in place of prior, limited transforms reduces the risk of error and failure in the real world, where choices may be made by application developers and hidden in software libraries. The committing security of UCX is shown in the ideal-cipher model, and its AE5-security in the standard model. To design UCX, we introduce and build a new primitive, that we call a Tweakable Committing Concealer, and that may be of independent interest.

We study error correction in a computationally bounded world, where errors are introduced by an arbitrary polynomial-time adversarial channel. Recent works construct seeded codes in this model, where the encoding and decoding procedure share a public random seed. They achieve significantly better tradeoffs between rate and error tolerance than what is possible information theoretically for unique decoding, essentially matching the parameters of the best known efficiently list-decodable codes. Over the binary alphabet, however, this is still well short of the optimal Shannon capacity with rate $R \approx 1 - H_2(p)$ for a $p < 1/4$ fraction of errors. Even heuristic constructions meeting this target were not previously known. We make progress towards this goal.

- $\textbf{Secret-Key Codes.}$ We first study secret-key codes, where the encoder and decoder share a secret key hidden from the adversarial channel. Lipton (STACS '94) constructed one-time secure secret-key codes achieving Shannon capacity in this setting, but it was unknown whether one can get CPA (resp. CCA) security where the adversary may query an encoding oracle (resp. also a decoding oracle). We construct CCA-secure secret-key codes achieving Shannon capacity via pseudorandom codes (PRCs). - $\textbf{Seeded Codes (Heuristic).}$ We can heuristically upgrade the resulting secret-key codes to seeded codes by publishing an obfuscation of the encoding/decoding procedures with a hard-coded secret key as a seed. Security holds in the ideal obfuscation model. - $\textbf{Public-key Codes.}$ We also consider public-key codes, where the decoder has a secret key and the encoder has the corresponding public key. We construct such CPA-secure public-key codes achieving Shannon capacity with unique decoding for $p < 1/4$ errors, and list decoding all the way to $p < 1/2$ errors, assuming PRCs and the subexponential security of standard crypto assumptions (e.g., LWE or DDH or QR or DCR). We also show how to get CCA security in the random oracle model. - $\textbf{List-Decodable Codes.}$ Finally, we consider list-decodable codes that can achieve Shannon capacity for even larger fractions of errors, all the way to $p < 1/2$. We construct such public-key CPA-secure codes in the plain model using PRCs, as well as CCA-secure ones in the random oracle model.

Our secret-key and public-key codes meeting Shannon capacity are also simultaneously pseudorandom codes.

Depth-robust directed acyclic graphs (DAGs) are an important combinatorial primitive in cryptography, with applications to memory-hard functions, proofs of space, and proofs of sequential work. These applications require node depth-robustness, yet constructing sparse graphs with strong concrete guarantees remains a longstanding challenge. By contrast, edge depth-robust graphs are easier to construct explicitly and achieve better parameters, motivating the problem of efficiently transforming edge-depth-robust graphs into node-depth-robust graphs. We give a new and substantially more efficient transformation from edge-depth-robust graphs to node-depth-robust graphs. We give a new and substantially more efficient transformation from edge-depth-robust graphs to node-depth-robust graphs. Prior work of Blocki and Cinkoske (ITCS 2021) gave a general transformation by replacing each node with an ST-robust graph, resulting in extraordinarily large overhead and relying on non-explicit components. In contrast, our transformation replaces each node with a single superconcentrator rather than an ST-robust graph, yielding an explicit construction whenever the input graph is explicit, with dramatically improved concrete efficiency.

Formally, given an $(e,d)$-edge-depth-robust graph $G$ with $N$ nodes and $m$ edges, our transformation generates a graph $G'=Transform(G_N)$ with $N' = O(m)$ nodes, constant indegree, and $(e/3,\, 2d-1)$-node depth-robustness. We also show that the transformation preserves fractional depth-robustness. Moreover, when $m=\omega(N)$, we show that our transformation can amplify depth --- overcoming a key limitation of prior work. In particular, for any parameter $d'$, we can obtain a constant-indegree graph $G'$ with $N' = O(m+d'N)$ nodes and $(e/3,\, (d-e)d')$-node depth-robustness, yielding asymptotically tighter results in the important setting where $m = \omega(N)$ and $e \geq d$ by setting $d' \sim m/N$. As an application, We provide a novel analysis of Schnitger's edge-depth-robust graph construction (FOCS 1983). We show that the graph $G_n$, which has $N=2^{n+1}-1$ nodes and $m \leq n2^{n}$ edges, is $(e,2d-1)$-edge-depth robust for all $e + d \leq 2^n$. Applying our transformation yields an explicit DAG on $N'$ nodes with maximum indegree $2$ and depth-robustness parameters $e = \Omega(N'/\log N')$ and $d = \Omega(N')$, matching the best known asymptotic trade-offs—even compared with non-explicit constructions—while improving the best previously known concrete ed-product lower bound by a multiplicative factor of 6.6.

We introduce WayFinder, a framework for generalizing the Delfs-Galbraith and SuperSolver algorithms for the supersingular isogeny problem. Our framework extends the search for elliptic curves with an orientation by an order containing $\mathbb{Z}[\ell \sqrt{-p}]$ to more general orders, and we derive a cost model for such generalisations. Our cost model not only works in a more general context, but also provides more accurate predictions when applied to SuperSolver. We instantiate WayFinder for orders containing $\mathbb{Z}[\ell_1\sqrt{-\ell_2p}]$ where $\ell_i$ are $1$ or primes such that the modular curve $X_0(\ell_2)$ has genus $0$. We then introduce a low-storage algorithm for computing an isogeny between two oriented supersingular elliptic curves, even when the curves are oriented by distinct orders. Together, these provide an algorithm that improves on the state of the art for solving the isogeny problem, and a cost model with potential applications to parameter selection in isogeny-based cryptography.

We study frequency estimation in the shuffle model of differential privacy under poisoning attacks, where corrupted users may deviate from the local randomizer to inject crafted in-domain messages. Existing shuffle-model protocols face a core tension: achieving low estimation error relies on flexible multi-message noise generation, which can amplify poisoning influence once messages are anonymized by shuffling.

To address this tension, we propose a symmetric binomial-sum noise distribution (i.e., $\mathrm{Bin}(n/2,p) + \mathrm{Bin}(n/2,1-p)$), which preserves high accuracy while limiting the impact of crafted in-domain messages. We realize this distribution via preprocessing-guided noise generation, which routes a balanced collection of mode flags through the shuffler so that each user receives a randomly assigned mode flag that fixes their noise-sampling behavior prior to shuffling. For binary estimation, our protocol requires a single Bernoulli trial per user and at most $2$ messages per user ($1.5$ on average), while bounding the worst-case poisoning influence of a single corrupted user by $O(1/n)$. We extend the protocol to histograms, including large domains via hashing, and provide formal privacy, accuracy, and robustness guarantees. Experiments on real datasets show that our protocols remain resilient under poisoning and reduce MAE by up to nearly $2\times$ over the strongest baseline at comparable per-user communication on small-domain workloads, and stay on par with it on large domains.

In this work, we construct (stateful) leakage-resilient circuits (LRCs) secure against bounded-output-length leakage functions computable by \(\mathsf{NC}^1\) circuits under the mild worst-case assumption \(\mathsf{NC}^1 \subsetneq \oplus\mathsf{L}/\mathsf{poly}\), without relying on any leak-free hardware components, thereby resolving the open problem left by Bogdanov, Ishai, and Srinivasan (Journal of Cryptology, 2021) and Wang (CRYPTO 2025).

Concretely, we first construct a leakage-tolerant circuit with succinct setup (sAI-LTC) secure against 2-adaptive \(\mathsf{NC}^1\) leakage, and then generically combine it with a 2-adaptive leakage-resilient composable encoding scheme to obtain the desired LRC.

We further give a direct non-black-box instantiation that optimizes the compiled circuit size at the cost of a slightly larger setup, matching the circuit size of Wang's construction that relies on leak-free hardware while using a more compact setup.

Finally, we show that our sAI-LTC generically implies a fine-grained multi-theorem non-interactive proof system for all \(\mathsf{NP}\), with compact common reference strings, perfect soundness, and multi-theorem zero-knowledge with offline simulation against \(\mathsf{NC}^1\) adversaries.

Shor demonstrated that the discrete logarithm problem in the multiplicative roup $\mathbb{Z}_{p}^{*}$, where $p$ is an odd prime, can be solved fficiently using a period-finding algorithm based on the quantum Fourier transform. In this paper, we propose a quantum-classical algorithm based on algebraic properties that do not rely on periodicity. Specifically, we show that the hardcore predicate for the discrete logarithm problem, which was introduced by Blum and Micali, can be reduced, using the swap test, to the problem of distinguishing between two Bernoulli distributions. In our algorithm, although the swap test is used as a quantum subroutine, most of the computation is performed classically. Moreover, the algorithm does not require the quantum Fourier transform.

Classically testing for the presence of anti-commuting operators on a quantum device is a critical tool underpinning recent progress in classical verification of quantum computation. While such tests can be based on cryptographic assumptions, known constructions rely on highly structured assumptions, e.g. trapdoor claw-free functions.

In this work, we seek to explain this state of affairs by constructing strong cryptography from (certain forms of) classical tests of anti-commutation. In particular, we formulate the notion of a test of non-commutation (ToNC), an interactive protocol between a quantum prover and classical verifier in which the prover's final-round response is obtained by measuring one of two binary observables ?₀, ?₁ depending on the verifier's challenge bit ?. We prove that, for a broad range of parameters, ToNC implies classical-communication key agreement (KA), and ToNC combined with one-way functions implies oblivious transfer (OT).

Along the way, we develop tools for and provide the first known results on hardness amplification for post-quantum KA and OT, where communication is classical but adversaries may be quantum. In particular, we prove the following results of independent interest. - Post-quantum hard-core measure theorem: For any efficiently sampleable high-min-entropy distribution ? over pairs (?,?) such that quantum circuits have advantage at most ? in predicting ? from ?, there exists a sub-distribution ?≼? of density 1-? on which ? is nearly optimally quantum-hard to predict. - Post-quantum interactive XOR lemma: Given any classically-interactive protocol, if quantum adversaries have advantage at most ? in guessing a private challenger bit ?, then two sequential repetitions reduce the advantage for predicting the XOR of the challenger bits ?₁⊕?₂ to at most ?² + negl(?).

Blockchain consensus protocols, also known as BFT state-machine replication, enable a system of $n$ players to decide an ever-growing chain of blocks. We consider partial synchrony: after an unknown time GST, messages sent by honest players are delivered within an unknown actual delay $\delta$, and a known bound $\Delta$ satisfies $\delta \leq \Delta$. This setting imposes $t
The main technical novelty is a certificate of exclusivity for a block $B$. It is shown by the next leader as evidence that players can safely vote for a child of $B$. A certificate of exclusivity is an interpolation between a quorum certificate and a timeout certificate, in that it is formed from a mix of votes for a unique block $B$ and complaint votes, proving that $B$ is the only non-dummy block that can still obtain a decision certificate for that iteration.

The other novelty of Hamster is the use of {overlapping iterations: after a process has supported a newer proposal, the protocol may still allow it to support a safe proposal of an earlier iteration}. This overlap is what allows old honest proposals to be decided in time despite players advancing iterations faster.

We also analyze another metric, called the {pessimistic block proposal time}, which is the time during which a bad leader can delay the proposal of a transaction in a block which will be decided. Hamster achieves a pessimistic block proposal time of $2\Delta+2\delta$, refined to $2\Delta+\delta$ for leaders not caught equivocating, down from $3\Delta+\delta$ for Simplex.

In addition to anonymity and traceability, which are the primary security properties of group signatures, non‑frameability is also defined (Bellare-Shi-Zhang, CT-RSA 2005). This property guarantees that even an adversary colluding with all authorities (the opener and the issuer) cannot produce a signature that frames an honest user, and it is regarded as a security notion that protects users. In this short note, we introduce a new perspective on non-frameability, namely that it can also protect the authorities, and we examine its significance in the context of anonymous auctions, a well‑known application of group signatures. We show that non-frameability serves as an effective countermeasure against situations in which a winning bidder falsely claims not to have placed a bid and accuses the organizer of forgery.

Federated fine-tuning of Large Language Models via Low Rank Adaptation (LoRA) faces a critical privacy-efficiency trade-off: low-rank factors can leak sensitive data, yet standard secure aggregation is restricted to linear operations. Existing solutions for aggregating matrix products (e.g., $\mathbf{B}_i \mathbf{A}_i$) either sacrifice exactness, depend on a trusted third party, or incur prohibitive costs at scale. We present SecLoRA, the first decentralized framework achieving exact aggregation of LoRA updates with linear communication complexity. The core of SecLoRA is a novel cryptographic primitive: Pairwise Composable Multi-Client Functional Encryption (PC-DMCFE). Unlike traditional functional encryption, which treats ciphertext recombination as an attack, the dual-encryption architecture of PC-DMCFE ($\mathsf{Enc}_A, \mathsf{Enc}_B$) is intentionally designed to harness this property. It allows any ciphertexts $\mathsf{ct}_A$ and $\mathsf{ct}_B$ to be arbitrarily paired and evaluated via a functional key to reveal their inner product. This unique property enables secure and decentralized aggregation of matrix products without losing LoRA's linear communication advantages. Furthermore, SecLoRA ensures round-isolated decryption to prevent temporal leakage without extra interaction. Evaluation shows that SecLoRA is practical for cross-silo deployments.

A private information retrieval (PIR) protocol enables a client to retrieve a bit from an $N$ bit database replicated among $k$ servers in such a way that each server learns no information about the retrieved bit. Modern PIR protocols with information-theoretic privacy (Efremenko, SICOMP, 2012; Dvir and Gopi, STOC, 2015; Ghasemi et al., STOC, 25) are based on matching vectors over a composite number $m$. To construct a PIR protocol from the matching vectors, these protocols use a decoding polynomial, a sparse polynomial that returns a non-zero value on 1 and returns zero on a certain set implied by the matching vectors.

Beimel et al. (CCC, 2012) abstracted the properties required by the transformation computed by the decoding polynomial, defining the notion of share conversion. In such a conversion, a set of parties is given shares of a secret in one secret-sharing scheme, and each party locally computes a new share (without any communication) such that the new shares are shares in a second secret-sharing scheme of a related secret. Beimel et al. showed that share conversion can replace the decoding polynomial in the PIR protocol of Efremenko and constructed a share conversion from the ring $\mathbb{Z}_6$ to the field $\mathbb{F}_{2^2}$. This share conversion cannot be computed by a decoding polynomial, as decoding polynomials convert shares from a ring $\mathbb{Z}_m$ to a finite field of characteristic $p$ such that $p$ does not divide $m$. Alon et al. (TCC, 2025) simplified and generalized the PIR protocols of Dvir and Gopi and Ghasemi et al., using share conversion; however, in this protocol, the share conversion is from a ring $\mathbb{Z}_m$ to a finite field of characteristic $p$ such that $p$ does not divide $m$.

In this paper, we study the power of share conversions. Our main result proves that if there is a $k$-party share conversion from a ring $\mathbb{Z}_m$ to a finite field of characteristic $p$ such that $p$ does not divide $m$, then there is a $k$ sparse decoding polynomial from a ring $\mathbb{Z}_m$ to a finite field of characteristic $p$. This result implies that using share conversion in the protocol of Alon et al. can only improve the communication complexity by a constant factor. In addition, we show that if there is a $k$-party share conversion from a ring $\mathbb{Z}_m$ to a finite field, where $m$ is a product of $r$ distinct primes, then $k\geq r+1$, i.e., the number of servers in the resulting PIR protocols using the appropriate matching vectors is at least $r+1$. A similar result was recently proved by Ghasemi and Kopparty (ITCS 26); our lower bound also applies to the case in which the characteristic of the field divides $m$.

Quantum cryptography is a rapidly developing area which leverages quantum information to accomplish classically impossible tasks. In many of these protocols, quantum states are used as long-term cryptographic keys, relying on the quantum no-cloning theorem to ensure that the keys cannot be copied by an adversary. Unfortunately, quantum state tend to decohere, and hence, persistent quantum memory is and will remain one of the most valuable and challenging resources for quantum computers. As such, it will be important to minimize the extent to which our protocols use persistent quantum memory.

In this work, we consider the case of one-shot signatures (OSS), and more general quantum signing tokens, important uncloneable primitives where quantum signing keys allow for signing a single message but not two. Very recently, the first OSS scheme was constructed unconditionally in a classical oracle model as well as in the standard model under cryptographic assumptions (Shmueli and Zhandry, CRYPTO 2025). We observe that the quantum memory required for these protocols is a large polynomial (in the security parameter).

The main contribution of this work is to significantly decrease the quantum secret key size, in some cases achieving the asymptotically optimal size. One of our schemes guarantees perfect correctness and the other one admits a parallel signing algorithm for long messages. We also achieve strong signature incompressibility, which implies a public-key quantum fire scheme (Çakan, Goyal and Shmueli, QCrypt 2025) with perfect correctness.

During the course of this work, we develop novel techniques for proving the security of cryptosystems using coset states, one of the main tools used in uncloneable cryptography.

Homomorphic Advanced Encryption Standard (AES) evaluation refers to evaluating the AES circuit with a fully homomorphic encryption (FHE)-encrypted secret key. Applications include in particular Transciphering, which converts AES-encrypted data into FHE ciphertexts without exposing the secret key.

Existing homomorphic AES evaluations show a clear separation between latency-oriented solutions and throughput-oriented solutions. CKKS-based methods exploit massive SIMD parallelism and focus on throughput by processing many AES blocks in parallel. They are hardly suitable for latency-critical settings. In contrast, TFHE-based methods process a small number of blocks efficiently. They are preferable for low-latency settings, but provide very limited throughput.

In this work, we show that AES-CKKS evaluation can achieve both interactive latency and high throughput. Our first variant is optimized for latency and decrypts a single AES block in only 34ms on an NVIDIA RTX-5090. This is more than 4× faster than recent TFHE-based state-of-the-art approaches. Our second variant is based on a new embedding of $\textrm{GF}(16)$, the finite field with 16 elements, into CKKS message space. It is optimized for throughput and processes up to 2048 AES blocks at once, achieving over 200KB/s throughput (a more than 3.1× improvement over the state-of-the-art CKKS-based approaches), while maintaining latency comparable to TFHE-based methods. To the best of our knowledge, this is the first AES-FHE evaluation algorithm combining good latency and throughput properties, bringing homomorphic outsourcing with AES within reach of real-time applications on constrained devices.

Our main ingredients are redundant structures that maximize SIMD utilization, improved algorithms for the SubBytes step (one of them being based on inversion in $\textrm{GF}(256)$ using CKKS), fusion of linear layers into bootstrapping, and carefully crafted FHE parameters.

We construct preimage sampleable function families on $q$-ary lattices [Gentry–Peikert–Vaikuntanathan, STOC'08] for which preimage sampling reduces to sampling uniform points of unitriangular lattices from simple polytopes: affine linear transforms on the $\ell_1$ and $\ell_\infty$ balls, and a scaled intersection thereof. We build the necessary samplers by adapting an algorithm of [Kannan–Vempala, STOC'97] and improving its analysis. This sampling requires only uniform bits and affine linear transforms on the uniform distribution on $[0,1]$. The collision resistance of these families relies on the short integer solutions problem [Ajtai, STOC'96] in various $\ell_p$ norms. Considering the Lee metric as the $\ell_1$ norm in $q$-ary lattices, we answer an open question to construct such families for the Lee metric [Hörmann–van Woerden, CRYPTO'24]. We also answer an open question of [Plançon--Prest, PKC'21] by sampling from polytopes with inradius smaller by a factor almost square root in the lattice rank. We provide a generic framework for constructing preimage sampleable function families from polytopes with sufficient conditions for realising it. While our parameters are worse than prior discrete Gaussian based constructions, such distributions are challenging from a physical security perspective.

Overbroad computer crime, intellectual property, and other laws are well known to create legal risks that can discourage essential research. Notable examples include the US Computer Fraud and Abuse Act and the UK Computer Misuse Act. Because such laws fail to distinguish malicious hacking from good-faith testing and research, researchers face serious legal risks for public-interest research activity like identifying software or hardware vulnerabilities or scraping data. Despite the research community's broad awareness of these risks, our understanding of their practical impacts is limited, as most of the community's knowledge comes from anecdotal evidence rather than systematic study.

We conduct the first qualitative study focused on researchers' lived experiences, to empirically document the *impacts of legal risks and threats* on research and researchers*, and *how researchers navigate legal risk situations*. Our study engages two participant groups: researchers with legal-risk experiences in the UK or the US ($N_R=36$), who discuss 130 projects and incidents spanning over three decades, and professionals that offer support to researchers navigating legal risks ($N_S=8$), who have collectively supported thousands of researchers. We thus provide an unprecedented big-picture view of researchers' experiences with legal risks. We synthesise actionable strategies for researchers, and our findings provide evidence to support policy reform.