arXiv:2611.17820v1 Announce Type: new Abstract: Previous work has shown that alignment training on individual LLM agents can fail to transfer to multi-agent settings. We investigate the underlying mechanisms for this failure, and explore interventions to preserve alignment trans…
⏱ Độ trễ thật của tab này: trung bình 7.3 giờ sau khi CVE được công bố (n = 5336, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
Previous work has shown that alignment training on individual LLM agents can fail to transfer to multi-agent settings. We investigate the underlying mechanisms for this failure, and explore interventions to preserve alignment transfer to multi-agent LLM teams. We focus on two sof…
arXiv:2611.10411v1 Announce Type: new Abstract: LLM-based agents extend LLMs with tool calls, memory, planning, and retrieval to act in external environments, but they are vulnerable to attacks at different workflow steps. Existing defenses, including prompt engineering and post…
arXiv:2611.11266v1 Announce Type: new Abstract: As enterprises delegate consequential work to multi-agent LLM systems, benign-looking requests can escalate into unsafe actions as they propagate across sessions through poisoned shared state, long-context documents, and trusted pe…
arXiv:2611.16588v1 Announce Type: new Abstract: Affected-version ranges in vulnerability databases decide which deployments scanners, patching pipelines, and incident responders treat as vulnerable, yet these ranges are often incomplete, so vulnerable releases are silently treat…
arXiv:2611.17818v1 Announce Type: new Abstract: Jailbreak attacks can circumvent the safety mechanisms of Large Language Models (LLMs) and lead to the generation of harmful or policy-violating content. We first examine eight jailbreak methods against an LLM-based filter and obse…
arXiv:2611.14781v1 Announce Type: new Abstract: Agents that perform state estimation using pretrained perception models, e.g., Vision-Language Models (VLMs), face the fundamental challenge that predictions are uncertain. Still, most approaches determinize these predictions into …
arXiv:2611.14864v1 Announce Type: new Abstract: An AI agent's decision not to act can itself become an attack surface. We study warning-induced over-abstention, an availability attack in which adversaries place fabricated risk warnings in low-trust content to prevent legitimate …
arXiv:2611.16693v1 Announce Type: new Abstract: Mobile GUI agents read the screen of a phone and operate apps on a user's behalf to complete multi-step tasks such as online shopping or messaging. Because the agent acts on whatever the screen shows, an attacker can embed maliciou…
arXiv:2611.17620v1 Announce Type: new Abstract: High-level behaviors such as sycophancy and hallucination correspond to directions in a model's activation space (Chen et al., 2025). These directions, known as persona vectors, can suppress undesirable traits either at inference t…
arXiv:2611.18055v1 Announce Type: cross Abstract: DeCompCert is a Rocq-verified decompiler for AArch64 assembly generated by CompCert. It reconstructs CompCert C through nine reverse passes, combining deductively verified transformations with translation validation. Untrusted OC…
arXiv:2611.18563v1 Announce Type: cross Abstract: Monitoring maritime activities is important for safety and security, particularly for detecting illegal activities, but remains challenging due to the size and complexity of the maritime domain. The Automatic Identification Syste…
arXiv:2611.16565v1 Announce Type: new Abstract: We ask whether small, open-weight decision models can support vulnerability discovery in open-source software at scale and what the surrounding system must provide. These models answer a typed question in one forward pass, returnin…
arXiv:2611.12970v1 Announce Type: new Abstract: Large Language Models (LLMs) show strong potential for social media content moderation, but their trustworthiness beyond overall accuracy remains underexplored. We introduce TrustMod-SM, a benchmark of roughly 29,000 instances acro…
arXiv:2611.10089v1 Announce Type: new Abstract: Large Language Models (LLMs) remain vulnerable to jailbreak attacks and harmful-content prompts, particularly under adversarial distribution shifts where static alignment pipelines fail to generalize. Although introspective methods…
arXiv:2611.10418v1 Announce Type: new Abstract: Semantic response caching reuses a cached response for a semantically similar query to improve LLM inference efficiency. However, query similarity alone can lead to unsafe reuse when safety conditions change. Existing approaches im…
arXiv:2611.16151v1 Announce Type: new Abstract: Hardware fault injection attacks threaten machine learning systems, yet their impact on reinforcement learning (RL) has received little attention despite the use of RL in safety-critical applications. This paper presents a security…
arXiv:2611.13577v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong capabilities across diverse applications, making both safety and utility essential for reliable deployment. Jailbreak attacks use diverse forms of adversarial prompting to bypass align…
arXiv:2611.13578v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong capabilities across diverse applications, making both safety and utility essential for reliable deployment. Jailbreak attacks use diverse forms of adversarial prompting to bypass align…
arXiv:2611.13227v1 Announce Type: cross Abstract: We introduce Latent Barrier Steering (LBS), a hierarchical semantic-to-path framework for safe flow-matching-based generative planning. Existing control-barrier-function (CBF) safety filters for diffusion and flow-matching planne…
arXiv:2611.13367v1 Announce Type: cross Abstract: An AI assistant writes small programs, and a gatekeeper must decide, from the code alone, whether each one may run. Suppose the rules are fixed: never perform a forbidden action, never let the output depend on a secret, always an…
arXiv:2611.10048v1 Announce Type: new Abstract: Large language models (LLMs) offer a scalable approach for annotating mental health and crisis-related social media content, but their reliability in safety-critical tasks remains unclear. This study evaluates LLM-based crisis-seve…
arXiv:2611.10054v1 Announce Type: new Abstract: Children and adolescents are increasingly interacting with generative AI and large language models (LLMs), yet little is known about how these interactions may influence their development, beliefs, and behavior. Existing research h…
arXiv:2611.10261v1 Announce Type: new Abstract: The phrase recursive self-improvement (RSI) refers to the idea of an AI system designing and creating another, better AI system, which in turn designs and creates an even better one, and so on. While the idea has a long history, it…
arXiv:2611.10279v1 Announce Type: new Abstract: Safety-aligned language models are known to suffer degradation in refusal behavior following domain-specific fine-tuning, even when the fine-tuning data is entirely benign. The predominant mitigation strategy, preference optimizati…
arXiv:2611.10037v1 Announce Type: new Abstract: Personal AI agents are increasingly deployed on user devices to execute actions involving real money and sensitive data, but their security under social engineering attacks has not been systematically evaluated. We propose SEA (Soc…
arXiv:2611.10056v1 Announce Type: new Abstract: Open-weight LLMs are routinely fine-tuned from public repositories, yet task-specific adaptation can silently erode safety alignment inherited from instruct-tuned bases. This is a supply-chain risk when organizations ship third-par…
arXiv:2611.10099v1 Announce Type: new Abstract: We study a safety harness that improves itself without touching model weights. Enmo Safety wraps a chat model with a deterministic input assessment, trigger-matched safety guidance, spotlighting of untrusted content, and an output …
arXiv:2611.11067v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in user-facing systems, where jailbreak attacks can bypass safety controls and induce harmful and policy-violating outputs. Recent model-internal detectors use hidden represent…