cập nhật 2 phút trước

⏱ Độ trễ thật của tab này: trung bình 7.1 giờ sau khi CVE được công bố (n = 5392, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

30
Aligning AI Teams
📄 Paper arXiv cs.AI 1 ngày 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
29
Auditable Authorization for LLM Agents: Empirical Evidence Across Model, Harness, and Workflow Layers
📄 Paper arXiv cs.AI 9 giờ trước

arXiv:2611.19237v1 Announce Type: new Abstract: Human approval provides effective control only if rejected work stops and authorized work completes. We formalize refusal safety and bounded authorization completeness, and audit three execution boundaries: the model selects a call…

🅲 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
SPLICE: Structured Prompt Local Iterative Combinatorial Evolution
📄 Paper arXiv cs.AI 9 giờ trước

arXiv:2611.18883v1 Announce Type: new Abstract: Natural language optimization (NLO) improves an agent by having a model critique and rewrite its natural language policy parameters: system prompts, tool instructions, reasoning directives, few-shot demonstrations. These artifacts …

🅲 hạng C
25
LLMs are Vulnerable to Malicious Requests with Indistinguishable Intent
📄 Paper arXiv cs.CR 1 ngày 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
Memory Safety Isn't All You Need: Code Reuse Attacks in Memory Safe Languages
📄 Paper arXiv cs.CR 9 giờ trước

arXiv:2611.18910v1 Announce Type: new Abstract: Memory safety rules out classical code reuse attacks that rely on arbitrary memory corruption, but does not eliminate code reuse altogether. Attacks such as object injection, prototype pollution, class pollution, DOM clobbering, an…

🅲 hạng C
24
When the Spec Sheet Lies: Injection Attacks on LLM-Generated Compliance Artifacts
📄 Paper arXiv cs.CR 9 giờ trước

arXiv:2611.19090v1 Announce Type: new Abstract: As Large Language Models (LLMs) become used more commonly across a variety of fields, a growing body of research has highlighted particular concerns surrounding model security. Notably, prompt injection attacks, where malicious ins…

🅲 hạng C
24
Designing Deceptive Model Organisms that Successfully Evade Auditing
📄 Paper arXiv cs.CR 9 giờ trước

arXiv:2611.20459v1 Announce Type: new Abstract: AI models can exhibit deceptive behaviors such as strategically underperforming on evaluations (sandbagging), faking alignment, or covertly acting on behalf of a hidden principal. Safe deployment therefore requires auditing techniq…

🅲 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 4 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
22
Safety Side Effects of Preventative Persona Steering: An Empirical Audit
📄 Paper arXiv cs.AI 1 ngày 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
22
DeCompCert: A Verified Decompiler for CompCert-Generated AArch64
📄 Paper arXiv cs.CR 1 ngày 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
22
Pairing AIS with RF: Analysis of a Markovian Approach for Maritime Data Fusion
📄 Paper arXiv cs.CR 1 ngày 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
20
TERM: Target-Free Jailbreak Defense via Entropy-Guided Residual Modulation
📄 Paper arXiv cs.CR 6 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 6 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 6 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