Latest news
-
Vulnerabilities via Help Net Security
Cybersecurity jobs available right now: October 20, 2026
Application Security Architect Riskified | Israel | Hybrid – View job details As an Application Security Architect, you will review architecture, design, and code to…
-
AI Security via arXiv cs.CR
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…
-
Threat Intel via arXiv cs.CR
ToolRosetta: 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…
-
Threat Intel via arXiv cs.CR
Under 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…
-
AI Security via arXiv cs.CR
Recording-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…
-
Threat Intel via arXiv cs.CR
Automated Rule Mutation for Emerging Attack Variants using Infrastructure-Aware Technique Proximity
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…
-
AI Security via arXiv cs.CR
SPIDES: 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…
-
Threat Intel via arXiv cs.CR
Empirical 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…
- Advertisement
-
AI Security via arXiv cs.CR
Unbounded Losses, Unchecked Inputs: Measuring the Safeguards of LLM Options-Trading Agents
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…
-
AI Security via arXiv cs.CR
RATION: 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…
-
Breaches via arXiv cs.CR
Can Agents Keep Secrets They Were Never Told? Benchmarking Latent Privacy Risks Across Sessions with MemJoin
arXiv:2610.24359v1 Announce Type: new Abstract: To support sustained interactions and personalized assistance, agents use long-term memory to retain and combine user…
-
AI Security via arXiv cs.CR
Defending Against Dormant Poisoning Attacks Across Language and Multimodal Agents
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…
-
Vulnerabilities via arXiv cs.CR
Narratives Mislead: An Empirical Study of How LLMs Misjudge CVSS Severity in Bug Bounty Reports
arXiv:2610.24623v1 Announce Type: new Abstract: Bug bounty platforms receive vulnerability reports faster than vendors can triage them, and Large Language Models (LLMs)…
-
Threat Intel via arXiv cs.CR
SecODD: Adapting the Operational Design Domain from Driving Autonomy to Autonomous Cyber Defense
arXiv:2610.24741v1 Announce Type: new Abstract: Security operations centers are beginning to delegate detection, triage, and containment to Autonomous Cyber Defense…
-
AI Security via arXiv cs.CR
Heart 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…
-
AI Security via arXiv cs.CR
LLM 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…
-
AI Security via arXiv cs.CR
From Trust Scores to Driver Decisions: An Abstaining Evidential Decision Layer for Event Validation in VANETs
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…
-
Threat Intel via arXiv cs.CR
Consistency Is the Attack Surface: Detecting Coordinated Retrieval Poisoning with Embedding Geometry
arXiv:2610.24834v1 Announce Type: new Abstract: Consistency-based defenses for retrieval-augmented generation (RAG) rest on an assumption that a sparse adversary breaks…
-
AI Security via arXiv cs.CR
The Missing Compliance Class: LLM Graders That Collapse Jailbreak Success, and a Free Check
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…
-
Vulnerabilities via arXiv cs.CR
Peer Pressure: Execution-Verified Co-Evolution of Attacker and Defender Populations for Code Security
arXiv:2610.24896v1 Announce Type: new Abstract: LLM code agents increasingly ship code with little oversight, yet defenders trained on static vulnerability datasets fall…