Papers

Inference-time pipelines often sample multiple outputs, filter them with a learned safety model, and return the proxy-feasible output with the highest learned reward. We show that this composition creates a two-stage failure: an imperfect safety proxy first contaminates the feasible set with unsafe outputs, and reward maximization can then amplify this residual contamination. We define safety hacking as selecting an output that passes the learned constraint but violates the true safety criterion. For constrained Best-of-$N$ sampling, we derive finite-$N$ bounds governed by the joint upper reward tails of safe and unsafe outputs within the proxy-feasible set. If unsafe-but-feasible outputs have the heavier tail, safety hacking becomes asymptotically certain as $N$ grows, even when false-positive mass and average safety- and reward-proxy errors are arbitrarily small. We also show that policies within a bounded $\chi^2$ divergence from the proxy-feasible reference distribution admit an $N$-independent safety-hacking bound, and instantiate this general coverage-control principle with constrained pessimistic sampling. Coverage control limits amplification but cannot repair a contaminated feasible set: admitted unsafe outputs may still be favored, and regularized selection is not necessarily safer than constrained Best-of-$N$ for every reward proxy. Toy and language-model experiments characterize both contamination and its reward-tail amplification, which exposes an inherent difficulty in inference-time scaling with learned safety models.

This paper presents computational results of cryptanalysis of AES using the Local Inversion by Black Box computations of the forward encryption and utilizes these results to develop a practically feasible approach for the key recovery of the full scale AES128 under Known Plaintext Attack (KPA). It is shown that complete recovery of unknown key bits is possible upto $80$ bits in a practically feasible time and memory in random KPA situation by sequential computation when remaining $48$ bits are known. The results of key recovery in $64$, $72$ and $80$ bit unknown cases are extrapolated to predict the period of the iterative sequence generated in the local inversion approach for the full $128$ bit unknown key case and a strategy is proposed to search the actual period by brute force parallel search of the sequence period with $10$ free bits defining the search space. Then it is shown that the actual key can be verified in polynomial time by fast powering of the forward encryption map. Hence this strategy shows that the key recovery problem for AES128 under KPA has a chance of success in practically feasible time for a majority of the plaintexts. Local inversion approach to cryptanalysis using black box computations is a universal method applicable to a vast variety of key recovery and map inversion problems. Hence the results presented in this paper are representative of estimates of cryptanalysis of other ciphers which can be considered almost as strong as AES128 as encryption functions.

Attacks against Internet-connected IoT devices continue to increase; however, transforming observed attack traffic into deployable intrusion detection system (IDS) rules remains largely a manual process. Recent studies have explored using large language models (LLMs) to generate IDS rules; nonetheless, existing approaches often require auxiliary information beyond observed traffic or generate rules without validating their detection logic against benign traffic. This study presents a verification-guided specification synthesis framework for generating Suricata rules directly from HTTP request traces. Instead of having an LLM generate IDS rules in a single step, an LLM first identifies a vulnerable parameter and synthesizes a semantic detection specification. These specifications are iteratively refined through counterexample-guided inductive synthesis (CEGIS), in which benign traffic samples serve as counterexamples during synthesis and verification. Verified specifications are then deterministically compiled into Suricata rules. Experiments on 281 real-world CVEs and benign traffic collected from real IoT devices show that the proposed method achieves a detection rate of 81.5% while maintaining a false positive rate of 0.0%. An ablation study also demonstrates that CEGIS-based verification improves detection performance while maintaining a low false positive rate.

Applications that deploy LLM agents keep revising the permissions their agents use. When authority is consumable, even widening a permission can break a legitimate workflow, because an early call may use up a grant that a later call needs. Checking individual requests, or watching one run succeed, misses this. We present Agenra, a policy language with a Lean enforcement core that tracks the values each call uses, resources discovered at run time, and authority consumed by earlier calls. Agenra treats safety and workflow preservation as separate properties. Our key idea is to certify a revision with a simulation between the old and new permission ledgers. Quota increases, appended grants and independent reorderings admit such simulations by construction, and Lean checks proposed simulations for other finite-quota revisions. The proofs use the deployed matching predicates and extend through the full monitor, covering discovered resources, payloads that are never enumerated, failed calls and approvals. They assume serialized calls and identical service results under both policies, and they trust the Python translation layer. On 51 authored revisions, the checks certify all 21 that preserve their clients and none of the 30 that do not, and every lost workflow is confirmed by replay. They also certify a real quota increase from an open-source agent application. In a report-delivery application, raising the send quota preserves every client yet permits a second approved send, so preservation does not imply safety.

Membership inference attacks expose whether individual records were used to train a model, yet existing attacks on diffusion models are largely heuristic and can require substantial query budgets. We introduce DIME (Denoiser Ideal Membership Error), a theoretically grounded and query-efficient framework for membership inference on diffusion models. Our starting point is an exact characterization of the optimal diffusion denoiser for a finite training set, which reveals that membership leakage is governed by the denoiser's implicit reconstruction error. This error decomposes into two complementary signals: a bias term, capturing reconstruction accuracy, and a previously unexplored local crowding term, capturing the geometry of nearby training examples. Both admit efficient estimators using only model queries, yielding a practical attack with as few as two queries. Across CIFAR-10/100, STL10-U, CelebA, and ImageNet, DIME consistently outperforms prior attacks at comparable or substantially lower query cost, improving TPR at 1% FPR by up to $3\times$; remarkably, its two-query variant can outperform existing 30-query baselines. Finally, we suggest, discuss, and evaluate specific defenses to counteract such powerful membership tests.

This paper proposes a Non-Fungible Token (NFT) soft pairing framework for Bluetooth service access control. Unlike conventional Bluetooth systems where pairing implicitly grants persistent service access, the proposed approach decouples native Bluetooth pairing from authorization without modifying the underlying protocol stack. The framework introduces a three-layer architecture consisting of a Bluetooth layer for connectivity, a blockchain layer for trusted execution and on-chain state verification, and an application layer where NFT soft pairing defines the authorization logic. In this design, Non-Fungible Bluetooth Tokens (NFBTs) represent user-side access credentials, while Non-Fungible Device Tokens (NFDTs) represent device identities. Their bidirectional on-chain binding forms a revocable and verifiable NFT soft pairing relationship. During access, users prove ownership of valid NFBTs through challenge-response signatures, and devices verify the corresponding on-chain state before granting service access. A prototype implemented with MetaMask and Ethereum demonstrates secure authentication, dynamic revocation, acceptable latency, and gas-efficient credential issuance based on ERC1155.

Machine-learning malware detectors often achieve high clean-data accuracy, but operational triage also requires evidence about uncertainty, novelty, robustness, interpretability, latency, and review cost. This paper presents EGAMA-RC, a risk-calibrated evidence-gated framework for memory-forensic malware triage. Building on SHAP-guided feature refinement, EGAMA-RC combines dataset-specific refinement, model-pool evaluation, adversarial and open-family testing, novelty scoring, explanation-conditioned evidence, and runtime-aware routing. Low-risk samples are accepted automatically, while uncertain, high-risk, or potentially novel cases are routed to review, escalation, or novelty-aware handling. Across three malware datasets and a frozen multi-seed protocol, the selected hybrid gate accepts 93.12% of pooled samples with 99.86% accepted accuracy and a 0.136% false-accept rate. Novelty calibration reduces over-restrictive review behavior while preserving a low unsafe-accept profile. XGBoost provides lightweight fast-path inference with p50/p95 latency of 0.0054/0.0059 ms per sample. The results show that dependable malware analysis requires risk-calibrated routing, novelty awareness, and controlled analyst review, not classification accuracy alone.

Despite their remarkable success, machine learning models, particularly in vision applications, are alarmingly vulnerable to a range of security threats. One key factor in the attack landscape is the distinction between white-box and black-box threat models, as the latter poses challenges that limit attack effectiveness when access to model information is limited. As a result, using Trusted Execution Environments (TEEs) enhances security for machine learning applications by protecting model confidentiality and execution integrity, effectively shifting the execution environment from the white-box to the black-box side of the threat model spectrum. While adopting TEEs for large vision models, e.g., Vision Transformers (ViTs), is crucial for enhancing security and privacy, significant challenges related to memory constraints and increased computational latency must be addressed, especially in time-sensitive edge applications where safety and privacy are paramount. The objective of this work is to enable large vision models to be fully hosted within TEEs, achieving GPU-level inference latency for time-sensitive edge vision applications while maintaining performance. To this end, we propose TEE-X, a TEE-aware acceleration framework that introduces a sensitivity-aware modularization technique and enables vectorization in TEE inference. This design is validated on OP-TEE for Arm TrustZone, configured to optimize performance on the NVIDIA Jetson AGX Xavier for efficient edge vision applications using ViT models. The findings reveal that TEE-X delivers an effective TEE-aware acceleration framework that achieves minimal accuracy-latency trade-offs while ensuring fast and secure edge inference for vision models.

Encrypted traffic classifiers often achieve high accuracy under matched training and testing conditions, implicitly assuming that deployment traffic follows the training distribution. TLS migration toward post-quantum cryptography (PQC) challenges this assumption because hybrid key establishment can reshape observable traffic without changing application labels. We frame this change as PQC-induced protocol drift and study its effects through closed-world HTTPS website fingerprinting using the deployed TLS~1.3 Hybrid-PQC group \texttt{\detokenize{X25519MLKEM768}}. We build a controlled, PQC-aware benchmark pairing Traditional (Non-PQC) and Hybrid-PQC traffic, then evaluate five representative classifiers and side-channel representations under matched-domain, cross-domain, and deployment-ratio settings. Collectively, the experiments show that PQC evolution does not remove learnable website information. Instead, it changes how that information appears in traffic, causing classifiers and feature combinations that perform well in-domain to lose reliability across cryptographic domains. By exposing the fragility of matched-domain evaluation, we offer strategic guidance, identify cross-domain robustness as a research priority, and recommend protocol-aware practices for dependable real-world encrypted traffic classification. The code is available at http://anonymous.4open.science/r/PQ-WF-Eval.

The emergence of multi-class malware attacks such as ransomware, spyware, trojans, etc., presents an increasing and serious threat to cybersecurity, particularly in resourceconstrained environments like IoT devices. Existing machine learning models have achieved nearly perfect accuracy in binary malware classification but fall short in terms of classifying malware families and individual malware. Additionally, the complexity of these multi-class malware attacks presents a significant challenge of detection in resource-constrained environments, as multi-class detection usually requires high computational capability. This research bridges the gap by enhancing the detection accuracy of multi-class malware classification as well as developing a lightweight model that can run efficiently on resource-constrained devices. In this paper, we propose a robust, lightweight machine learning model featuring LightGBM classifier with SMOTE oversampling and SOM-US undersampling techniques for data balancing, as well as well-engineered feature selection through Genetic Algorithm. The model performed better than the current state-of-the-art models developed on the same dataset in both malware family classification (4 classes) and individual malware type classification (16 classes) with accuracy of 89.1% and 76% respectively. Thus, maintaining a balance between classification accuracy and computational efficiency in resource-constrained environments. Furthermore, we propose another model using Random Forest classifier with an accuracy of 91.2% in malware family classification and 78.7% in individual malware classification. Demonstrating a significant enhancement in terms of accuracy from the current state-of-the-art models.

Public blockchains expose the complete transaction graph, and the privacy protocols deployed to obscure it rely almost exclusively on elliptic-curve cryptography, whose discrete-logarithm foundations fall to Shor's algorithm. Because ledgers are immutable, every anonymity set published today under classical assumptions can be retroactively deanonymized by a future quantum adversary. Transitioning to post-quantum alternatives remains challenging, as strict smart-contract resource limits prohibit native on-chain verification of computationally intensive post-quantum proofs. To address these challenges, we present Obscura-PQ, a decentralized, non-custodial post-quantum privacy protocol that verifies natively on the Algorand blockchain. Its core is a setup-free lattice linkable ring signature over the cyclotomic ring $\mathcal{R}_q = \mathbb{Z}_q[X]/(X^{512}+1)$. A deposit is a Ring-SIS binding commitment to a short secret; a withdrawal proves knowledge of a ring opening via an AOS/Borromean-style challenge chain over two response-sharing linear relations with rejection-sampled short responses, while publishing a deterministic Ring-LWE serial number for double-spend detection. We reduce double-spend soundness and linkability to Ring-SIS, theft resistance to Ring-SIS for honestly generated deposits, and anonymity to Ring-LWE and an explicit decisional linking assumption in the classical random-oracle model. To overcome strict on-chain opcode and storage limits, Obscura-PQ evaluates verification relations entirely in the NTT domain. We split forward NTTs across opcode-pooled execution phases and stream oversized proofs through refundable box storage, enabling $O(1)$ membership and double-spend checks. We provide a complete Algorand testnet implementation, demonstrating native on-chain verification of a post-quantum privacy protocol under strict smart-contract limits.

The Rust programming language is widely credited with eliminating entire classes of memory-safety and concurrency vulnerabilities, but the security implications of adopting it in practice extend well beyond memory safety. This paper presents a critical review of prior work on Rust's security posture in industrial settings, and extends that analysis in a direction the original study did not cover: backend web development. We first assess the strengths and limitations of the existing vulnerability classification of Rust against C, C++, and Java under the SANS Top 25, OWASP Top 10, and the 19 Deadly Sins of Software Security frameworks, identifying gaps including limited empirical validation, a small interview sample, and the absence of a secure development lifecycle discussion. We then contribute an original comparison of Rust against Node.js and Django using the same three-level classification (Rare and Difficult, Safeguarded, Unprotected), supported by side-by-side code experiments for out-of-bounds writes (CWE-787), use-after-free (CWE-416), and race conditions (CWE-362). Our results indicate that Rust's compile-time guarantees dominate at the systems layer, while managed backend frameworks offer stronger built-in defenses at the application layer, suggesting that Rust adoption in web contexts requires complementary safeguards rather than reliance on language-level safety alone.

Financial fraud detection relies heavily on centralized machine learning models. This creates serious data privacy risks. Federated Learning (FL) decentralizes data processing, but financial regulations still require models to be transparent. This means using Explainable AI (XAI) tools such as TreeSHAP. Recent cybersecurity research shows a problem with this approach. Sharing high-fidelity SHAP explanations exposes the federated network to Membership Inference Attacks (MIAs). This dissertation proposes and evaluates DP-FedSHAP. It is a new architecture that applies client-level differential privacy only to post-hoc TreeSHAP vectors. It is compared against a Weight-Level DP baseline, which perturbs the trained model directly instead. Using the highly imbalanced IEEE-CIS Fraud Detection dataset, this study measures the trade-off between explanation fidelity, privacy preservation, and the model's Area Under the Precision-Recall Curve (AUPRC).

In today's digital landscape, high-efficiency video coding (H.265/HEVC) has emerged as the most widely used video coding standard, employing selective encryption schemes to protect the privacy of video content while maintaining efficient compression performance. However, existing coefficient scrambling methods impose a significant computational load, leading to increased bit rate overhead due to encryption, longer execution times, and insufficient safety measures. To address these issues, a new coefficient scrambling scheme based on chaotic maps is proposed. This approach leverages the pseudorandomness, ergodicity, and sensitivity to initial conditions inherent in chaotic maps to generate highly unpredictable coefficient distributions, thereby strengthening security while preserving low complexity. Unlike conventional scrambling, chaotic maps ensure minimal correlation between encrypted coefficients, enhancing resistance against statistical and differential attacks. Additionally, the scrambling conditions are specifically designed to minimize the impact on the bit rate overhead. Furthermore, when combined with syntax element encryption (SEC), which includes motion vector difference (MVD), quantized transform coefficients (QTC), and luma intraprediction mode (Luma IPM), this method effectively distorts video content. The proposed scheme operates synchronously with slices, ensuring that the decryption of video content remains intact even if some slices are lost. Additionally, a random sequence generated by AES-CTR is incorporated with the H.265 encoded stream to protect against chosen-plaintext attacks.

The significant upsurge in vehicle traffic presents a considerable challenge in the pursuit of smart mobilization and transportation (SMT) worldwide. Current approaches primarily focus on vehicular traffic management through congestion prediction but fall short in addressing essential objectives such as traffic reduction and appropriate vehicle selection to alleviate congestion in smart cities ($SmCt$). To address these concerns, this work introduces a novel Neighbor-Embedded Graph Neural Network-based Crowd Delivery Traffic Management (NeCDM) Model, comprising two key components: the Traffic Congestion Prediction Unit (TCPu) and the Traffic Observation and Management Unit (TOMu). The TCPu utilizes Graph Neural Network (GNN) optimization to accurately predict traffic flow levels at various delivery stations within $SmCt$ ecosystems. Additionally, the TOMu facilitates the intelligent selection of the most suitable delivery vehicles for fulfilling crowd delivery requests ($CDR$). This work emphasizes the potential of crowd delivery as a feasible solution for achieving SMT goals while adhering to smart city parameters ($\mathcal{SCP}$s), such as reduced carbon emissions, shorter travel times, and minimized travel distances. The proposed model achieves notable improvements in computational efficiency, including reductions of up to 4.03% in L1 loss ($\pounds$), 16.66% in L2 loss ($\pounds_{rmse}$), and 7.64% in computation time.

Decentralized federated learning (DFL) is a promising paradigm for autonomous nodes to collaboratively train AI models without relying on a central server. However, existing DFL solutions do not guarantee global model consistency, a critical requirement for collaborative mission-critical scenarios where model divergence undermines decision uniformity and safety. This lack of consistency also amplifies vulnerability to Byzantine adversaries, who exploit the decentralized network topology and weak synchrony to perform equivocation and model poisoning attacks against individual victims. This paper introduces DFL-C, a novel Byzantine-resilient DFL architecture that enables decentralized nodes to perform collaborative training with global model consistency. At its core, DFL-C integrates an asynchronous common subset (ACS) consensus protocol into the DFL workflow to ensure all nodes aggregate a uniform set of model updates to establish global model consistency, despite individual Byzantine equivocation. DFL-C further implements a dual-domain trust scoring mechanism to provide resilience against data-domain Byzantine manipulations including model poisoning attacks. This mechanism complements the consensus protocol, significantly reducing the latter's runtime. Our experimental results demonstrate that DFL-C maintains model accuracy while achieving global model consistency under Byzantine behaviors with moderate consensus overhead. Notably, when compared with the state-of-the-art DFL solution BALANCE (Fang et al.) that does not provide model consistency, DFL-C achieves better model accuracy against untargeted model poisoning attacks and comparable resilience against backdoor attacks, with the advantage widened under non-IID scenarios.

Private bidding is a process in which participants submit sealed bids, ensuring that their content remains hidden from other bidders during the bidding window. This is essential in competitive environments to ensure a fair and independent evaluation of all proposals. While (public) blockchain enables decentralized bidding and its transparency offers advantages such as public verifiability, without a Trusted Third Party (TTP), current methods struggle to verify whether a bidder is eligible. We propose a framework that leverages Self-Sovereign Identity (SSI) to address these issues by certifying the bid's eligibility and authenticity using the now-established SSI framework. To allow participants to prove they meet the requirements while keeping their bids secret, our model uses Verifiable Credentials (VCs) and cryptographic primitives such as Zero-Knowledge Proofs (ZKPs).

Regulation (EU) 2024/886 obliges European payment service providers to settle euro credit transfers in under ten seconds, around the clock. This removes both the overnight batch window in which anti-money-laundering (AML) analytics traditionally ran and the settlement delay that made recovery possible, forcing detection, explanation and decision inside a single-digit-second envelope. We present KONTOGRAPH, an end-to-end AML pipeline for the SEPA Instant rail built under a self-imposed 200 ms 99th-percentile budget, and report an empirical study on 1,562,860 simulated payments with injected typologies and deliberately incomplete labels. Three findings are of interest beyond the system itself. First, a temporal graph network with per-node memory improves PR-AUC over a gradient-boosted tabular baseline from 0.0053 to 0.1717, a paired day-blocked bootstrap difference of +0.166 with 95% CI [0.105, 0.241]; per-node memory alone more than doubles the score. Second, expressing each feature once and compiling it to three execution backends, with equivalence enforced by property-based tests that perturb the future, surfaced three point-in-time violations that code review had passed–each of which would have inflated reported performance. Third, and most consequential for practice, exporting the deployed tree ensemble to ONNX changed only $7.4 \times 10^{-8}$ in mean score yet altered 0.26% of decisions and inflated the alert volume by 12%, because 32-bit accumulation perturbs scores across a cost-optimal threshold of $3.98 \times 10^{-4}$. We argue that a serving-format conversion must be treated as a model change until measured, and that fidelity metrics for subgraph explainers can be vacuous when candidate neighbourhoods are small–a null result we report in full.

We introduce MCSI, a two message key exchange we design over the CSIDH class group action, in which each party sends its ephemeral public element under an authenticated encryption keyed by the value the two static keys determine. The design gives implicit mutual authentication, hides the ephemeral element from an eavesdropper, and lets a recipient discard an unauthenticated message after one tag check rather than after an evaluation of the group action, which is four orders of magnitude more expensive. On the analytic side, we prove that our protocol is correct with zero error, and prove three statements in the random oracle model, all reducing to the strong parallelisation problem: indistinguishability of the session key against a passive adversary, confidentiality of the blinded ephemeral element, and integrity of the blinded transport. None uses the decisional group action assumption, which is false for class group actions of non-prime discriminant. We also show that a blinding key cannot come from the session secret it is meant to establish. To instantiate the design we select parameters and show that a prime chosen for elliptic curve discrete logarithms is unusable: for $p = 2^{521}-1$, the NIST P-521 prime, the action admits no efficiently evaluable generator. On the practical side, we build and test the design. We implement the protocol twice, in C and independently in Python, cross check the two, and measure what a session costs in field operations, time and memory. We also audit our code for secret dependent control flow: the field arithmetic and the symmetric layer show none, while the group action leaks the key by construction, and two hundred timings separate two keys whose one-norms differ by five out of 370. Finally, we state what we do not prove, among them security under ephemeral key reveal, forward secrecy of the blinding, and constant time execution.

Smart contracts power blockchain applications such as DeFi and NFTs. However, once deployed, they cannot be modified. Even minor bugs can result in significant financial losses. Current AI-based repair methods rely on linear reasoning, which leads to the accumulation of errors and unreliable patches. Our method combines document parsing, static analysis, and Tree of Thoughts reasoning. We first convert audit reports into structured data. Then we use Slither to locate the exact vulnerable code. Our three-step framework explores multiple repair paths simultaneously, evaluates options, and eliminates poor choices. Finally, we verify patches through compilation and manual checks. We test our method on 50 real vulnerabilities from Code4Rena. Our method achieves a 62% single success rate and an 84% top-3 success rate, outperforming ContractTinker by 12 and 6 percentage points, respectively. We also increase the proportion of fully effective patches to 44%, while reducing defective patches from 38% to 22% and invalid patches from 10% to 4%. This approach overcomes the limitations of linear reasoning and makes smart contract repair more accurate and practical.

Security teams must prioritize vulnerabilities before exploitation evidence is complete. Existing signals, such as CVSS, EPSS, advisories, and public exploits, are useful but fragmented and time-sensitive; retrospective rankings can therefore overstate performance by using evidence unavailable at decision time. We present ThreatLens, a simple yet effective and deployment-realistic framework for CVE prioritization. ThreatLens ranks vulnerabilities at each review point using only cutoff-valid evidence and learns from future CISA KEV entries as weak supervision for exploitation relevance. Under forward-in-time, CVE-disjoint evaluation, ThreatLens significantly outperforms CVSS, EPSS, and rule-based evidence-fusion baselines. On the held-out test split, ThreatLens surfaces 80.0% of future KEV CVEs in the top 20, over three times EPSS at the same budget, and reaches 95.9% in the top 50. Early-warning analysis further shows that ThreatLens identifies a substantial fraction of subsequent KEV entries before formal catalog inclusion, supporting timely, evidence-grounded triage.

Automated testing discovers vulnerabilities faster than developers can investigate and repair them, leaving an interval in which known memory corruptions remain exploitable. End- to-end LLM repair agents can shorten this interval, but they synthesize open-ended code changes and commonly validate them only by replaying a proof of concept (PoC). This weak oracle accepts patches that silence the observed crash by changing unrelated behavior, making unintended deployment risky. We present CodeMechanic, a bug-property-guided system for generating constrained mit- igations for spatial memory corruption. Instead of asking an LLM to generate a permanent repair, CodeMechanic reconstructs the violated memory-safety property from the crash, validates the dereferenced pointer and its buffer range, and inserts a local fail-stop guard before the dangerous access. The guard terminates execution when the boundary check fails. The resulting mitigation deliberately trades availability for security: it can convert potential remote code execution into controlled termination while developers investigate the root cause and prepare a permanent repair. CodeMechanic combines a two-dimensional static and dynamic context extractor with in-prompt debugging knowledge and stepwise val- idation to limit the effect of LLM errors. On 101 real-world ARVO bugs, the first attempt of CodeMechanic produces 47.6% more plausible patches (i.e., patches that pass PoC- replay validation) than the best baseline while using 91% fewer tokens. Manual audit further shows that CodeMechanic produces 3.4x - 4.3x more patches semantically equivalent to developer-written repairs.

Large Language Models (LLMs) have been integrated into complex ecosystems (e.g., Code Agents), while Indirect Prompt Injection (IPI) attacks have emerged as critical barriers to their safe deployment. Attackers exploit LLMs' indistinguishability between "instructions" and "data" to manipulate LLMs via maliciously injected instructions. Existing defenses, however, face an intractable safety-utility trade-off: most guardrails either incur high latency or suffer from severe over-refusal. In this paper, we first demonstrate that LLMs can separate instruction from data intrinsically with both theoretical and empirical evidence. Inspired by this insight, we propose AEGIS (Adaptive Ensemble Guard for Injection Shielding). AEGIS extracts instruction-sensitive projectors to identify malicious instructions and leverages a Unified Multi-Layer Consensus mechanism that aggregates topologically distinct signals across the network depth. Empirical evaluations show that AEGIS achieves remarkable detection performance against both heuristic and optimization-based attacks compared to baselines, highlighting its potential to mitigate IPI. Code is available at https://github.com/xaddwell/AEGIS

Fine-grained attribution of AI-generated text is becoming increasingly important for accountability and auditing, yet existing multi-bit watermarking methods still struggle to simultaneously preserve the base generation distribution, support high-capacity payloads, and remain recoverable after editing. We present PURA, a provably unbiased and robust multi-bit watermarking method for text attribution. Instead of perturbing token probabilities directly, PURA embeds payloads in the latent sampling space via keyed inverse transform sampling, and recovers them by treating observed tokens as soft interval evidence and aggregating such evidence across the sequence. This design preserves the base generation distribution exactly while substantially improving recovery stability under post-editing and channel perturbations. Building on this recovery paradigm, we further develop a unified robustness analysis and show that, under bounded attack strength, the per-bit error probability decays exponentially with sequence length. Extensive experiments show that PURA substantially outperforms existing unbiased baselines in the high-payload regime. For example, when embedding 36 bits in 200 tokens, PURA achieves a 91.7% message match rate, more than three times that of the strongest unbiased baseline, while preserving text quality and remaining statistically close to unwatermarked text, and incurring only millisecond-level verification overhead. Our code is available at

Black-box LLM services have emerged as a practical deployment paradigm. Nevertheless, their opacity also hinders the systematic assessment of security risks and complicates copyright auditing for model owners. Black-box LLM fingerprinting, which identifies the underlying LLM identity through query-response interactions, offers a promising way to bridge this gap. Existing approaches typically collect responses from target LLM services using a fixed set of queries and perform poorly in the presence of realistic and complex configurations (e.g., system prompt and sampling settings). To overcome these limitations, we propose AdaptPrint, a response-adaptive fingerprinting method for revealing hidden LLM identities in black-box LLM services. AdaptPrint integrates three progressive response consistency probing strategies: Direct Probing, Continuation Probing, and Follow-up Probing. AdaptPrint determines the final LLM identity by performing similarity matching among candidate LLMs. Experimental results show that AdaptPrint significantly outperforms state-of-the-art methods among 27 candidate models, achieving Top-1, Top-3, and Top-5 accuracies of 80.6%, 90.3%, and 92.1%. AdaptPrint also demonstrates strong robustness across different defense strategies and decoding parameters.

Hardware hacking competitions have emerged as practical platforms for evaluating security weaknesses in complex System-on-Chip (SoC) designs while promoting security-aware verification and tool development. This paper presents a systematic study of SoC security verification through open-box hardware hacking competitions, focusing on practical vulnerability analysis strategies, observed findings, and lessons for security-aware verification. We present a multi-strategy vulnerability analysis methodology, combining simulation-based verification, formal verification, lint analysis, Large Language Model (LLM)-assisted bug detection, and coverage-guided hybrid fuzzing. Representative vulnerability findings are analyzed to illustrate how different techniques expose complementary classes of security flaws, and we derive practical lessons for pre-silicon security verification. Finally, we discuss how competition benchmarks can support the reproducible evaluation of emerging hardware security techniques and guide future security-aware EDA research.

Reconfigurable intelligent surfaces (RISs) hold great potential to enhance coverage, spectral efficiency, and communication security by intelligently configuring their reflecting elements. When owned by a neutral RIS operator, these elements can be offered as resources for which legitimate receivers and eavesdroppers compete. This paper investigates such competition and evaluates its impact on the physical-layer security performance of legitimate receivers. To model the competition, we develop a sequential RIS auction (SRA) framework, in which a bundle of RIS elements is auctioned in each round through a first-price sealed-bid mechanism, with each bidder submitting its bid based on the achievable rate gain and remaining budget. We then formulate the sequential bidding process as a Markov game by specifying its states, actions, rewards, and state transitions. To solve the game, we propose a multi-bidder deep deterministic policy gradient (MADDPG)-based multi-bidder reinforcement learning (MARL) approach under centralized training and decentralized execution (CTDE), enabling legitimate receivers and eavesdroppers to learn bidding strategies that maximize their long-term economic surplus. Numerical results show that, under the considered eavesdropper bidding strategies, the RL-based strategy enables legitimate receivers to achieve the highest secrecy rate per unit cost, outperforming random and fixed strategies and approaching the ideal physical-layer upper bound.

Bitcoin's Unspent Transaction Output (UTXO) model enables public analysis of fund flows, but users often merge transactions into Shared Send Mixers (SSMs) to obscure these flows. Untangling SSMs to recover original subtransactions is an NP-complete problem. While a practical untangling algorithm exists, it fails to classify 1.4% of SSM transactions due to computational time limits. This paper introduces four novel heuristics that exploit structural weaknesses in real-world SSM transactions to resolve these timeout cases: preemptive grouping, connectable singleton, ambiguous pairing, and knapsack fallback. We provide theoretical proofs validating each heuristic and integrate them into an optimized pipeline. Applied to timeout transactions, our approach classifies 98.5% of previously unresolved cases, reducing the overall unclassified transaction rate from 1.4% to 0.021% of all SSM transactions. Our open-source implementation and comprehensive evaluation on the complete Bitcoin blockchain demonstrate that the heuristics effectively untangle previously intractable transactions, enabling more accurate flow analysis and deeper structural insights into cryptocurrency transaction patterns.

I built a protocol whose premise is that a stranger can re-run my claims offline and get the same answer. An outside engineer audited it and broke it: a bundle whose headline numbers were false verified clean, the cheapest forgery four bytes. I merged his fix, then pointed my own instruments at the fixed verifier and found the same defect four more times, in places his audit did not reach. The cheapest is one capital letter. The unifying defect is not cryptographic or exotic: a check that reports success along a path where it never examined anything. Vacuous pass is a working label, not a discovery; Section 4 names the literatures already occupying it. So I stopped collecting anecdotes and measured. At f59fb62, under the extraction rule of Section 6, the verifier exposes 112 refusal sites; 75 could be deleted with the whole suite and every tamper fixture still green, a score of 0.330. Three of the four hand-found forgeries fall in surviving classes; the fourth is an obligation with no refusal site. Scored alone, the sixteen-fixture corpus built to prove the verifier can refuse catches 10. Testing the refusals themselves took it to 0.941, then to 1.000 at 92e4548 over a grown population of 146 sites; those denominators differ and the series between them is non-monotone, so Section 7.5 carries all eleven, not just the five rows of Table 2. Fixing the four found defects instead moved 37/112 to 39/119, leaving the pre-existing sites at 37. Seven times during this study my own measuring tools reported success while measuring nothing; four were built to detect this class, and one returned a perfect 1.000. Every number here is self-measured on a system I wrote, over a registry that is a closed loop of my own repositories; the one external data point is the audit of Section 2.2. That is stated here rather than buried: it is the paper's credibility, not a caveat.

Securing IEC 61869-9 Sampled Values (SV) is challenging because process-bus communication must satisfy stringent real-time constraints while supporting standardized high-rate publication profiles. This paper presents an experimentally validated security framework that combines lightweight per-frame authentication for operational SV traffic with post-quantum-capable key establishment protocol. For message integrity, the proposed method applies field-selective authentication employing optimized Chaskey-12 to reduce per-packet computational overhead. For trust establishment, the paper introduces an ML-KEM-based pairwise authentication and key-establishment procedure. The pairwise protocol is analyzed in the Quantum Random Oracle Model and is also verified with AVISPA tool under the Dolev-Yao adversarial model. A C-based publisher/subscriber prototype is implemented on a two-node process-bus testbed. Performance is evaluated across the eight IEC 61869-9 SV packet profiles using HMAC-256, AES-GMAC-128, Blake-2s, Chaskey-12, and a compiler-optimized Chaskey-12 implementations. These results indicate that optimized Chaskey-12 achieves ~90% lower latency than HMAC on SV packets. The proposed security framework is a practical and scalable candidate for protecting IEC 61869-9 SV traffic on resource-constrained digital-substation devices.