Searcharxiv⌕ Search

SEARCH · Searcharxiv

Search Searcharxiv

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 181 records · Page 10Linked to original sources
arXiv2026

A Queryable Graph-Based Security Analysis Framework for O-RAN

The Open Radio Access Network (O-RAN) replaces vendor-locked RANs with a modular and interoperable architecture that fosters competition and accelerates innovation. With this openness comes increased complexity and a larger attack surface, making security a critical concern. Today, assessing O-RAN security requires manually cross-referencing dozens of specifications, vendor whitepapers, and academic studies, which is error-prone and static. In this paper, we present a graph-based framework that transforms this static corpus into a single, queryable database. Our graph representation contains over 350 nodes and more than 1,250 relationships, distilled from specifications, academic papers, open-source projects, and vulnerability databases. To keep this resource current, we integrate a hybrid data extraction pipeline that couples deterministic parsing of structured specifications with Large Language Model (LLM)-assisted extraction for evolving specifications and unstructured literature. Querying the graph reveals three actionable findings within our curated corpus: critical infrastructure such as the O-DU, SMO, and O-Cloud carries dozens of specification-level threats yet has little or no empirical coverage; memory-safety weaknesses account for 11 of the 21 CWE occurrences associated with the analyzed CVEs; and fuzzing uncovered 18 of the 20 CVEs attributed to research papers. We provide the database, pipeline, and queries as open-source artifacts.

cs.CR↗
arXiv2026

AgentHijack: Visual Patch Attacks on Multimodal Computer-Use Agents

This paper presents an end-to-end evaluation framework for image-triggered command injection against computer-use agents (CUAs). The goal is to test whether a local visual patch can induce verifiable environmental consequences along the full chain of screenshot input, VLM generation, action parsing, and environment execution. We train and deploy patches on author-controlled GitHub Pages pages and a locally deployed CSDN clone, and evaluate them in real environments across five open-source or publicly available GUI-agent or vision-language-model (VLM) backends. Our experiment aggregates 600 instance-level online cases, with T-ASR, TAPR, and E2E-ASR reaching 84.5%, 47.0%, and 20.3%, respectively. Trajectory analysis further shows that in some successful cases the agent first executes a malicious terminal command and then continues the original benign task. These results indicate that optimized local visual signals can affect not only VLM outputs but also propagate through the execution pipeline of open CUAs and create real environmental risk.

cs.CR↗
arXiv2026

Recovering Process Variables from Industrial Network Traffic via Search-Based Optimization

Process variables (PVs) provide the process evidence needed for process-aware security monitoring in industrial cyber-physical systems (CPSs). However, existing supervisory infrastructures expose only the subset of PV values recorded by historians, leaving many additional runtime PV values unobserved. To address this incomplete process visibility, we study the problem of recovering PV fields and their semantics directly from raw industrial network traffic through protocol reverse engineering (PRE). In this setting, existing PRE methods face two practical challenges: PV-carrying communication is mixed with heterogeneous runtime traffic, and PV-carrying payloads are often long and deployment-specific. Mixed runtime traffic obscures the PV-carrying communication paths, while long payloads create a vast segmentation space in which early segmentation errors can propagate and corrupt the recovery of later fields under sequential inference. In this paper, we formulate the recovery of PV fields from raw network traffic as a search-based optimization problem. Our key insight is that non-sequentially identifying correct segmentations in such a vast segmentation space can be cast as an optimization problem and addressed by searching for near-optimal solutions. We propose PVParser to approach this goal. PVParser first reduces the search space by identifying the PV-carrying payloads from network traffic via a periodic pattern detection mechanism. It then employs a modified Monte Carlo Tree Search to explore near-optimal segmentations, reducing error propagation from incorrect early boundary decisions. Experiments on three representative industrial CPS datasets demonstrate that PVParser achieves high accuracy and F1-score in PV-carrying payload localization and PV field inference, outperforming six state-of-the-art PRE approaches by a significant margin.

cs.CR↗
arXiv2026

Strong but Brittle: Simple Attacks Subvert Reasoning-based Safety Guardrails

Open-weight Large Reasoning Models (LRMs) are approaching the capabilities of their frontier counterparts but pose significant safety concerns, as they are difficult to patch or monitor post-release. To prevent misuse, reasoning-based safety guardrails, where models explicitly reason on safety justifications before answering, have become a promising primary defense, achieving near-perfect refusal rates on harmful queries. We show that this strong defense is alarmingly brittle and can be subverted by embarrassingly simple attacks to elicit extremely forbidden questions, such as `How to kill a man without being caught?' Specifically, we identify one systematic vulnerability from the reasoning-then-answer mechanism: the stage-transition logic that governs when safety reasoning begins and ends can be trivially manipulated. Based on this finding, we develop four simple yet effective red-teaming methods that systematically subvert different stages of the guardrails, either by bypassing reasoning entirely or exploiting it to produce targeted harmful content. These methods achieve attack success rates up to 90\% across five benchmarks on multiple LRM families. Our findings reveal that reasoning-based guardrails are necessary but not sufficient and must be paired with robust triggering mechanisms and stronger base-model alignment. Code is in https://chenxshuo.github.io/bag-of-tricks/.

cs.CR↗
arXiv2026

Deep Research Agents Brings Deeper Harm

We reveal that Deep Research (DR) agents systematically expose safety risks: simply submitting harmful queries that a standalone LLM would reject outright can elicit detailed and dangerous reports from DR agents. Empirical analysis reveals that the advantages that make DR agents powerful unintentionally make them vulnerable: both the research role assignment (e.g., Planner) and the multi-step execution mechanism weaken alignment of the base LLM, leading to severe safety breaches. Through linear probe analysis of internal hidden states, we demonstrate that role assignment suppresses refusal awareness by shifting representations away from safety boundaries. Besides, multi-step execution distributes harmfulness across individual steps, preventing alignment mechanisms from being activated throughout the research process. Exploiting these vulnerabilities, we design Intent Hijack (i.e., rephrasing harmful queries as academic research) and Plan Injection (i.e., manipulating execution plans) to further examine the safety risks of DR agents. Extensive experiments show that our methods achieve near-perfect compliance and elicit detailed, actionable reports that significantly exceed standalone LLM outputs in technical depth and applicability. These results demonstrate alarming misalignment in DR agents and underscore the urgent need for tailored alignment techniques. Our code is available in https://schen.app/deeper-harm.

cs.CR↗
arXiv2026

AndroTruth: A Reliable Benchmark Android Malware Dataset Derived from Technical Expert Reports

Reliable family labels are essential for Android malware analysis, yet most widely used benchmarks derive such labels from aggregated VirusTotal engine outputs. Because antivirus vendors differ in detection logic, naming conventions, and signature updates, these labels are often inconsistent across engines and unstable over time, which introduces substantial noise into downstream empirical evaluation. To address this problem, we construct AndroTruth, an Android malware family benchmark whose labels are derived exclusively from traceable expert technical analysis reports rather than AV-consensus voting. AndroTruth spans 2016 to 2025 and contains 8,172 malware samples from 187 families. Our statistical results show that automated labeling tools can exhibit a misleading consensus failure mode in which AVClass2 and ClarAVy agree with each other yet jointly disagree with expert ground truth on 25.38% of samples with explicit labels from both tools. Experimental results show that, under expert-verified supervision, representative classifiers such as Meta-MAMC and AndMFC achieve accuracy above 96%. When trained with real-world AV-derived labels and evaluated against expert ground truth, however, their performance drops to only about 60% accuracy and about 35% macro-F1. ClarAVy confidenceaware filtering can improve family grouping quality, but cannot replace expert-verified labels for exact family naming. Together, these results demonstrate that label reliability is a first-order factor in Android malware family evaluation and highlight the need for expert-verified benchmarks.

cs.CR↗
arXiv2026

Behind Harmful Compliance: Behavioral and Mechanistic Divergence Across LLM Jailbreaks

Open-weight language models can be rendered unsafe through several parameter-level interventions, yet models with matched harmful compliance can exhibit fundamentally different failure modes. We compare harmful supervised fine-tuning (SFT), harmful reinforcement learning with verifiable rewards (RLVR), and refusal-feature abliteration in Qwen2.5-7B and Llama-3.1-8B using harmfulness, capability, self-audit, safety reflection, representation similarity, and refusal-direction repair. All three routes reach near-ceiling harmfulness, but SFT causes the broadest capability loss and representational drift; abliteration yields localized, family-dependent refusal-feature suppression; and RLVR largely preserves base-model capability, explicit safety judgments, and representation geometry while retargeting behavior toward compliance. RLVR models consequently remain unusually responsive to safety-reflection prompts despite complying under direct prompting. We further find that harmful RLVR induces capability-blind compliance: models claim to complete unavailable actions and fabricate information about nonexistent entities. Targeted RLVR calibration substantially reduces this false acceptance without restoring safety or degrading general capability. These results show that harmful compliance, harm recognition, and capability awareness are separable behavioral axes, and that self-audit and hallucination patterns are not necessarily robust safety signals under adaptive post-training.

cs.CR↗
arXiv2026

Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense

Despite advances in safety alignment, large language models remain vulnerable to continuously evolving jailbreaks. Existing fine-tuned safety classifiers cannot adapt to these evolving attacks, while adaptive memory-based guardrails tend to over-refuse benign queries that resemble stored attacks. We propose Membrane, a self-evolving guardrail built on Contrastive Safety Memory (CSM): each cell pairs the conditions for blocking a harmful query with those for permitting a superficially similar benign request. Without retraining, Membrane evolves CSM by distilling each harmful interaction and its benign counterpart into a contrastive cell indexed by the underlying attack strategy, so that one cell generalizes across topical variants of the same mechanism. At inference, retrieved cells serve as grounding context for precise safety decisions. Across model-level safety on HarmBench and agent-level safety on AgentHarm, Membrane achieves the highest F1 on all six modern jailbreak attacks. Notably, benign refusal on AgentHarm stays at 7-14%, well below the 28-85% range of prior guards. Memory cells also retain 87-88% F1 under cross-attack transfer and remain stable under memory poisoning.

cs.CR↗
arXiv2026

Quantum Algorithm for Elliptic Curve Discrete Logarithms with Space-Efficient Point Addition

The Elliptic Curve Discrete Logarithm Problem (ECDLP) is a fundamental problem in cryptography, and reducing the resource requirements of quantum algorithms for solving ECDLP is an important goal. In this work, we present a space-efficient quantum algorithm for solving the ECDLP over prime fields, achieving an implementation with only $3n+6\lfloor \log_2 n \rfloor+O(1)$ logical qubits and $1056n^3/\log_2 n+O(n^2)$ Toffoli gates, where $n$ is the bit-length of the prime. For a 256-bit prime-field curve, our construction requires only 835 logical qubits, reducing the previous best estimates of 1098 and 1175 logical qubits by Chevignard et al. [EUROCRYPT 2026] and Babbush et al. [ArXiv Preprint 2026], respectively. The key to our improvement is a new space-efficient reversible modular inversion circuit, which addresses the dominant space bottleneck in affine-coordinate point addition. Starting from the extended Euclidean algorithm (EEA), we refine the register-sharing technique of Proos and Zalka by introducing length registers and location-controlled arithmetic to compactly store and update intermediate variables. We further optimize the reversible update procedures and construct the corresponding controlled arithmetic circuits, resulting in a modular inversion circuit implemented by only $2n+6\lfloor \log_2 n \rfloor+O(1)$ logical qubits and $229n^2+O(n\log_2 n)$ Toffoli gates. This modular inversion circuit together with mid-circuit measurements and classical feed-forward operations provides a space-efficient controlled affine point-addition circuit and a complete implementation of Shor's algorithm for ECDLP.

quant-ph↗
arXiv2026

Privacy-Preserving RAG by Concealing Sensitive Information from External LLMs

Retrieval-Augmented Generation (RAG) is widely used to improve the performance of Large Language Models (LLMs) in answering user queries. Existing privacy research on RAG has focused on preventing unauthorized users from accessing sensitive data. However, another important problem that is often overlooked in RAG privacy research is that external generators have access to the query and the retrieved documents, which may contain confidential information that could potentially be misused or accessed for unintended purposes. In this paper, we introduce the Sensitive Entity Alias Generator (SEAG), a privacy-preserving framework that empowers users to utilize powerful third-party generators without disclosing sensitive information. SEAG introduces a lightweight model that locates sensitive entities, generates corresponding aliases, and constructs an entity replacement table. The table is used to replace sensitive words in the user's query and in the retrieved documents before they are forwarded to an external generator. For this purpose, two datasets were constructed: one for fine-tuning SEAG models to generate entity replacement tables, and another for evaluating the entire SEAG framework. The experimental results demonstrate the success of the SEAG framework. As for the User metric, which measures the ability of the model to provide a correct response to the user while hiding sensitive information from the external generator, all SEAG models achieved over 80% accuracy. Additional analysis further evaluated the ability of SEAG models Qwen-3, LLaMA-3.2, and Phi-4 to hide all sensitive entities within given documents. The results show good performance with total accuracies of 77.83%, 76.73%, and 74.91%, respectively.

cs.AI↗
arXiv2026

ARMOR: Manifold-Oriented Training for Adversarially Robust Aerial Object Detection under Data Scarcity

Aerial object detection is increasingly deployed in real-world applications, but models remain vulnerable to physical, universal adversarial patches that cause them to miss objects. Furthermore, defenders face the practical constraint of training data scarcity: aerial imagery is costly to collect and label, so a deployment site typically yields hundreds of images rather than the tens of thousands that adversarial robustness benchmarks assume. To tackle model vulnerability and training data scarcity, we propose Adversarial Robustness with Manifold-Oriented Training (ARMOR), a novel defense that realizes the core insights of on-manifold adversarial training (OMAT) in low-data regimes. ARMOR builds on the insight of OMAT to model the data manifold - the compact structure capturing the data's relevant features - to learn and robustify these features during training. While OMAT relies on the data-intensive operations of training large generative models and adversarial training to achieve this, ARMOR adopts a data-efficient approach that reuses labels the detection task already supplies: ARMOR (i) masks image backgrounds to retain object-relevant features, and (ii) injects randomized patches on objects to improve feature robustness. Our low-data experiments with physically-realizable adversarial patches evaluate both query-free transfer attacks and defense-aware attacks. ARMOR maintains strong clean performance of over 0.90 model confidence, while improving adversarial robustness by up to 0.32 in model confidence over state-of-the-art defenses. Physical experiments with printed patches confirm that these gains survive deployment. Overall, ARMOR translates insights from manifold-based training to defend object detectors amidst training data scarcity.

cs.CV↗
arXiv2026

Ranked by the Matcher: A Reproducibility Audit of Knowledge Graph Extraction from Threat Reports

Security teams and researchers choose knowledge-graph extraction tooling for threat reports on the strength of published triple-F1 scores, yet those scores depend on how predicted triples are matched to gold annotations. We could reimplement the stated matching rule for only five of twelve inspected systems. Re-scoring ten system outputs on shared documents under eight protocols reverses eleven of forty-five pairwise orderings; one fixed prediction set spans 0.16--0.70 F1. On an external, human-adjudicated set, no mechanical matcher---lexical, embedding, or entailment---agrees with the reviewers more than seven times in ten; an LLM judge agrees far more often. To separate component effects from matcher rewards, we build CTIForge, whose deterministic validation layer can vary while extraction is held byte-identical. Across seven tested deployment configurations, no hosted backbone loses precision under validation and every offline one does. Backbone, decoding, and prompting covary across those configurations; on the one backbone we could serve both ways, serving alone reproduces the split. It coincides with a roughly 2.8-fold increase in actions explicitly disputing entity type, consistent with hand-written rules encoding the conventions of the extractor against which they were developed. We release the pipeline, protocol suite, and per-triple audit records.

cs.CR↗
arXiv2026

Privacy Leakage in Federated Learning: Gradient-Based Client Identity Inference and Defenses for Inertial Sensing in Vehicular Edge Networks

As vehicular networks move toward 5G/6G edge intelligence, federated learning (FL) is widely promoted as a privacy-preserving way for vehicles and infrastructure to train shared models without exposing raw sensor data. Yet the updates clients transmit still leak enough information to identify who sent them, which threatens the anonymity that safety-critical V2X applications assume and adds to existing concerns over adversarial ML, model poisoning, and backdoor attacks. We study server-side client identity inference from transmitted weight deltas using inertial (IMU) measurements, evaluated on the UCI Human Activity Recognition (HAR) benchmark as an accessible proxy for the IMU streams produced onboard connected vehicles. Across five attack classifiers and five non-IID partitions, an honest-but-curious server recovers client identity with near-perfect accuracy (approximately 1.000) from undefended updates, confirming a concrete identifiability risk. We then quantify the privacy-utility trade-off of a lightweight clip-then-noise defense by sweeping Gaussian noise (sigma in {0.00, 0.05, 0.10, 0.20, 0.50, 1.00}) at fixed clipping (C=1.0), and report formal (epsilon, delta)-DP budgets through Renyi accounting. A practical region (sigma in [0.1, 0.2]) drives attack accuracy to near-random while costing under 5% relative FL accuracy. Ensemble FL supplies complementary structural privacy with a 1/K anonymity-set bound and no noise penalty. Results are supported by cryptographic (SHA-256) train/evaluation gradient disjointness, three seeds, and a count-normalized attacker-advantage metric. We position HAR explicitly as a proxy and discuss what validation on true vehicular telemetry would require.

cs.CR↗
arXiv2026

Bait-and-Recover: Poisoning Internal Refusal Signals to Defend LLMs against White-Box Editing Jailbreaks

Open-weight large language models face a low-cost white-box threat from representation engineering attacks. Attackers can estimate refusal directions and search for projection-matrix edits that suppress safety alignment while preserving general capabilities, within minutes on a single GPU and without gradient-based training. We propose Bait-and-Recover, a weight-level defense that places a bait adapter where attackers read activations and a paired recovery adapter at the subsequent layer. Trained via gradient routing, this decouples the observation path from the behavior path. By actively poisoning the residual signal used for measurement, Bait-and-Recover disrupts the attacker's edit search, while the recovery layer restores clean downstream computation. Across four open-weight models, our defense raises the minimum refusal rate against white-box edit searches from 16.25% to 71.75% under a strict behavior-preservation budget (KL <= 0.10), with negligible impact on general benchmarks. By invalidating the core measurement assumption of these attacks, observation-path poisoning offers a practical complement to behavior-level safety training.

cs.CR↗
arXiv2026

SAFEGuard: Detect Optimization-Based Jailbreak Attacks Through Harmful Semantic Analysis and Fluency Measurement

Despite the significant efforts devoted to aligning large language models (LLMs) with human values and ensuring safe deployment, recent work has revealed that LLMs remain vulnerable to adversarial jailbreak attacks that can bypass safety guardrails and elicit harmful responses. Many defense methods are proposed to detect jailbreaks but they are limited in their effectiveness to counter wide-range optimization-based jailbreak mechanisms that can yield highly fluency-optimized or harmful semantic obfuscated prompts. To tackle this challenge, we propose a unified detection framework SAFEGuard which incorporates a hybrid fluency measurement based on cross-layer distribution distance and perplexity, and the analysis of harmful semantics through gradient matching. Our method is grounded in a paramount observation: high fluency prompts maintain their malicious intention close to harmful prompts while harmful semantic obfuscated prompts often inject gibberish token sequences. Our evaluation demonstrates that SAFEGuard consistently outperforms state-of-the-art baselines and achieves significant improvement in accuracy across different optimization-based jailbreaks. This underscores the effectiveness of SAFEGuard against evolving jailbreak attacks.

cs.LG↗
arXiv2026

Multimodal Resource-Exhaustion Attacks on Vision-Language Models via Joint Pixel-Prompt Optimization

Resource-exhaustion attacks against autoregressive vision-language models (VLMs) typically assume unimodal threat models, treating the image branch as the primary optimization surface while holding user-visible prompts fixed. Even recent loop-centric variants remain confined to this single-channel paradigm, leaving the exploitation of availability unexplored as a cross-modal optimization problem over jointly controllable input surfaces. We introduce Joint Pixel-Prompt Optimization (JPPO), the first compound adversarial framework elevating the visible prompt to a first-class adversarial variable alongside image perturbations. Under a restricted joint-input threat model, JPPO performs coupled, stagewise optimization over both the pixel and prompt surfaces. This produces synergistic cost amplification, mechanistically distinct from loop-dependent failures, exhibiting negligible loop incidence in our experiments. Evaluating five open-source VLM families on MS COCO and ImageNet under an 8/255 infinity-norm budget, JPPO achieves over 4.6x latency and 5.3x energy amplification on Qwen2.5-VL-7B, and over 36.6x latency with 32.7x energy amplification on BLIP-2. This represents the strongest cost amplification among directly compared baselines while requiring substantially fewer optimization iterations. Ablations confirm this amplification arises from multimodal coordination rather than prompt length or isolated modalities. These findings reveal structural blind spots in current VLM serving defenses, motivating cost-aware robustness evaluation as a first-class security requirement for multimodal deployments.

cs.AI↗
arXiv2026

From Review to Authorization: Key-Isolated Threshold Signing for LLM Agents

Autonomous LLM agents can turn untrusted content into effectful actions such as payments and permission changes. If the same process interprets this content and controls a reusable signing credential, prompt injection can cross the judgment boundary and reach execution authority. We present KITA, a review-to-authorization architecture that keeps the user's personal secret signing key and every threshold signing-key share outside all LLM processes. Under threshold signature unforgeability and our system assumptions, compromising the proposer and fewer than t reviewer-signer domains cannot produce a valid authorization for a new action without signing contributions from t distinct domains. Thus, any such authorization includes a share from an uncompromised domain, bound to the canonical action and released only after authenticated reviewer approval. This establishes execution-bound authorization integrity. We implement the complete reviewer-to-executor path with a structured-output LLM adapter and threshold BLS. Six system tests validate quorum gating and message binding at this interface, while cryptographic microbenchmarks measure the online signing path and its scaling behavior.

cs.CR↗
arXiv2026

Structurally Close, Temporally Distant: Measuring Security Exposure in Long-Horizon LLM Agents

Long-horizon LLM agents interact with untrusted content, persistent memory, external state, and sensitive tools. Existing analyses often characterize attacks by the number of execution steps between malicious input and a downstream action. We show that temporal remoteness can overstate security separation in stateful agents. We introduce a provenance-aware execution graph linking agent events through deterministic state, identifier, and tool provenance, and define \emph{influence distance} $\DI$ as the shortest structural path from an untrusted source to a sensitive action. We compare it with \emph{sequence distance} $\DT$, the shortest injection--sink path in the ordered trajectory. Since the influence graph contains every sequence edge, $\DI \leq \DT$; $\Gap=\DT-\DI$ measures the separation hidden by step count. Across 454 injection--sink pairs from 360 long-horizon AgentDojo trajectories over OpenAI's \texttt{gpt-4o-mini} and \texttt{gpt-4o} and Claude's Haiku 4.5 and Sonnet 4.6, $\Gap>0$ for 96.9% of pairs, with a median gap of 9 hops; 91.0% remain decoupled after removing the largest provenance-only edge class. On AgentDojo's banking suite, 33.8% of 231 pairs from 377 trajectories decouple through different provenance mechanisms. Among 274 OpenAI pairs, $\Gap$ does not independently predict attack success after controlling for $\DT$, attack family, and backend ($β_{\Gap}=0.066$, $p=.088$). At matched thresholds $k=2,3$, a deterministic $\DI$-based pre-execution gate blocks five attack sinks missed by a sequence-only gate with no additional benign blocking, although the paired gain is not significant ($p=.0625$). Execution structure therefore reveals proximity hidden by step count and can support targeted runtime intervention. We measure candidate influence pathways rather than causal attribution.

cs.CR↗