cập nhật 9 phút trước

⏱ 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.

31
Aligning AI Teams
📄 Paper arXiv cs.AI 15 giờ trước

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…

🅲 hạng C
28
Aligning AI Teams
📄 Paper HF Daily Papers 4 ngày trước

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…

🅲 hạng C
28
Tail-risk-aware Agent Safety: Constraining Tail Risks Across Multi-step LLM Agent Workflows
📄 Paper arXiv cs.AI 6 ngày trước

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…

🅲 hạng C
26
LLMs are Vulnerable to Malicious Requests with Indistinguishable Intent
📄 Paper arXiv cs.CR 15 giờ trước

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…

🅲 hạng C
24
Robust Task-Aware State Estimation from Pre-trained Perception
📄 Paper arXiv cs.AI 3 ngày trước

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 …

🅲 hạng C
24
Safety Side Effects of Preventative Persona Steering: An Empirical Audit
📄 Paper arXiv cs.AI 15 giờ trước

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…

🅲 hạng C
24
DeCompCert: A Verified Decompiler for CompCert-Generated AArch64
📄 Paper arXiv cs.CR 15 giờ trước

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…

🅲 hạng C
24
Pairing AIS with RF: Analysis of a Markovian Approach for Maritime Data Fusion
📄 Paper arXiv cs.CR 15 giờ trước

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…

🅲 hạng C
23
Look Here, Then Decide: Small Decision Models in a Harness Find Memory-Safety Vulnerabilities at Scale on Commodity GPUs
📄 Paper arXiv cs.CR 3 ngày trước

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…

🅲 hạng C
23
META-IR: Meta-Introspective Reasoning for Adaptive Safety Alignment in LLM
📄 Paper arXiv cs.AI 6 ngày trước

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…

🅲 hạng C
23
Beyond Query Similarity: Safety-Conditioned Cache Routing for LLM Response Reuse
📄 Paper arXiv cs.AI 6 ngày trước

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…

🅲 hạng C
20
TERM: Target-Free Jailbreak Defense via Entropy-Guided Residual Modulation
📄 Paper arXiv cs.CR 5 ngày trước

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…

🅲 hạng C
20
POEM: Output-Relative Block-Sparse Attention for Long-Context Prefilling
📄 Paper arXiv cs.CR 5 ngày trước

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…

🅲 hạng C
20
Latent Barrier Steering: Hierarchical Safety for Generative Planning
📄 Paper arXiv cs.CR 5 ngày trước

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…

🅲 hạng C
20
Is Recursive Self-Improvement Safe?
📄 Paper arXiv cs.AI 6 ngày trước

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…

🅲 hạng C