Red-Teaming Multi-Agent Attacks for Loss-of-Control Risks
arXiv:2610.24052v1 Announce Type: new Abstract: AI agents are growing more capable and persistent, and are being deployed in ever larger numbers. As more start collaborating, AI control measures must...
View ArticleToolRosetta: Surface-Form Invariance of Tool-Call Guards
arXiv:2610.24055v1 Announce Type: new Abstract: Step-level guards for tool-using agents are evaluated on tidy JSON tool calls, but deployed coding agents act through execute_bash and execute_code tools...
View ArticleUnder the Skin: Backdoor Infection in Multimodal Large Language Models
arXiv:2610.24058v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved impressive performance in generating text conditioned on inputs from different modalities. In this...
View ArticleRecording-Aware Evaluation of Multimodal OT Intrusion Detection
arXiv:2610.24128v1 Announce Type: new Abstract: Machine-learning-based intrusion detection systems (IDSs) for operational technology (OT) are commonly evaluated on benchmark datasets in which normal...
View ArticleAutomated Rule Mutation for Emerging Attack Variants using...
arXiv:2610.24162v1 Announce Type: new Abstract: Detection rules are typically crafted based on specific observations of an attack. While these rules are effective for particular attack instances, their...
View ArticleSPIDES: Information-Flow Control for Browser Agents
arXiv:2610.24277v1 Announce Type: new Abstract: Browser agents automate complex workflows by reading and acting on arbitrary page content, but this flexibility exposes them to prompt injection attacks...
View ArticleEmpirical Analysis of TEE-Enabled Rollup Designs
arXiv:2610.24284v1 Announce Type: new Abstract: Layer 2 (L2) rollups have become the dominant scaling solution in Ethereum. At the core of these systems lies the rollup sequencer, a component that...
View ArticleUnbounded Losses, Unchecked Inputs: Measuring the Safeguards of LLM...
arXiv:2610.24289v1 Announce Type: new Abstract: Large language model (LLM) agents now place options orders at retail brokers, and developers publish open-source options agents faster than anyone has...
View ArticleRATION: Towards Quantitative Risk-Based Access Control for AI Agents
arXiv:2610.24311v1 Announce Type: new Abstract: AI agents increasingly interact with external environments to complete complex user tasks. These interactions can lead to unexpected behavior and expose...
View ArticleCan Agents Keep Secrets They Were Never Told? Benchmarking Latent Privacy...
arXiv:2610.24359v1 Announce Type: new Abstract: To support sustained interactions and personalized assistance, agents use long-term memory to retain and combine user information across sessions....
View ArticleDefending Against Dormant Poisoning Attacks Across Language and Multimodal...
arXiv:2610.24379v1 Announce Type: new Abstract: Recent work shows that attackers can implant dormant malicious behaviors that remain hidden at release but emerge after benign fine-tuning. As foundation...
View ArticleNarratives Mislead: An Empirical Study of How LLMs Misjudge CVSS Severity in...
arXiv:2610.24623v1 Announce Type: new Abstract: Bug bounty platforms receive vulnerability reports faster than vendors can triage them, and Large Language Models (LLMs) are increasingly considered for...
View ArticleSecODD: Adapting the Operational Design Domain from Driving Autonomy to...
arXiv:2610.24741v1 Announce Type: new Abstract: Security operations centers are beginning to delegate detection, triage, and containment to Autonomous Cyber Defense (ACD) agents at execution time....
View ArticleHeart Signal (ECG) as Vibration Signature for Human Authentication Using TinyML
arXiv:2610.24761v1 Announce Type: new Abstract: Ensuring data security in the era of Artificial Intelligence (AI) and deepfake technology requires robust biometric systems. Conventional methods such as...
View ArticleLLM Trojans that Increase Response Lengths and Cost
arXiv:2610.24784v1 Announce Type: new Abstract: Management of the token-based costs of using LLMs has emerged as a significant problem. Some frontier-model providers charge five times per response...
View ArticleFrom Trust Scores to Driver Decisions: An Abstaining Evidential Decision...
arXiv:2610.24810v1 Announce Type: new Abstract: Trust management in vehicular ad hoc networks is highly active, yet the decision that a driver needs, whether a reported event is real, has received far...
View ArticleConsistency Is the Attack Surface: Detecting Coordinated Retrieval Poisoning...
arXiv:2610.24834v1 Announce Type: new Abstract: Consistency-based defenses for retrieval-augmented generation (RAG) rest on an assumption that a sparse adversary breaks: a poisoning campaign may modify...
View ArticleThe Missing Compliance Class: LLM Graders That Collapse Jailbreak Success,...
arXiv:2610.24872v1 Announce Type: new Abstract: Jailbreak papers report an attack success rate, the share of responses that deliver the harmful request, and read it as a property of the target model....
View ArticlePeer Pressure: Execution-Verified Co-Evolution of Attacker and Defender...
arXiv:2610.24896v1 Announce Type: new Abstract: LLM code agents increasingly ship code with little oversight, yet defenders trained on static vulnerability datasets fall behind adapting adversaries. We...
View ArticleCAT-RAG: Improving Secure Code Generation with Category-Aware Agentic Retrieval
arXiv:2610.24907v1 Announce Type: new Abstract: Despite rapid progress in LLM-based code generation, security vulnerabilities remain widespread, and retrieval-augmented code generation (RACG) can...
View Article![[imports/adg/photos/213899875_Police-Car-Lights-2.jpg]](http://wehco.media.clients.ellingtoncms.com/imports/adg/photos/213899875_Police-Car-Lights-2_t600.jpg?4326734cdb8e39baa3579048ef63ad7b451e7676)
![Suupeas – Fall in Dream (2026-10-09) [Single, FLAC 24bit/48kHz]](http://getimg.link/images/2026/10/17/442240.md.jpg)
