cập nhật 1 giờ 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.

28
What a CAGE 4 Score Measures: An Audit of a Learned Cyber-Defense Benchmark, Its Reference Defenders, and the Tables Built on Them
📄 Paper arXiv cs.CR 5 ngày trước

arXiv:2611.14068v1 Announce Type: new Abstract: CAGE Challenge 4 is the benchmark on which learned multi-agent cyber defenders are compared. We reproduce its two reference defenders, KEEP and H-MARL Expert, in a pinned container and show that three things read from it measure le…

🅲 hạng C
28
Agentic Attribution of Cloud Resource Ownership
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.11340v1 Announce Type: new Abstract: Security tools raise findings across cloud environments, and AI agents now investigate and prioritize them. A finding is still resolved by people: it has to reach the people responsible for fixing it and accountable for the resourc…

🅲 hạng C
27
EvoX: Rethinking the Agent Harness as a Runtime Policy
📄 Paper arXiv cs.AI 3 ngày trước

arXiv:2611.15006v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly interact with tools and environments, yet plausible model decisions do not always translate into successful execution due to tool-call mismatches, interrupted workflows, and unsupporte…

🅲 hạng C
27
PolicySniff: Inferring Agent Policy States through Shared-GPU Execution
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.16158v1 Announce Type: new Abstract: LLM agents apply approval settings, such as whether to ask before a consequential tool call, through instructions in their system prompt, and operators keep these settings confidential by restricting access to prompts and responses…

🅲 hạng C
26
Co-Sight Harness: Externalized Control Assets and Deterministic Enforcement for Long-Horizon Business Agents
📄 Paper arXiv cs.AI 16 giờ trước

arXiv:2611.17696v1 Announce Type: new Abstract: Long-horizon business workflows fail in two ways: errors accumulate as a chain of activities lengthens, and the knowledge an activity needs is written in a different vocabulary from the user's request. We study whether such workflo…

🅲 hạng C
24
Interpreting Coding Agents Through Their Behavioral Trajectories
📄 Paper HF Daily Papers 5 ngày trước

Standard coding-agent benchmarks primarily evaluate binary task success, treating execution as a black box and obscuring the behaviors that produce those outcomes. We analyze a large corpus of 143,209 execution trajectories from 125 agent configurations spanning 117 unique models…

🅲 hạng C
24
Safety Side Effects of Preventative Persona Steering: An Empirical Audit
📄 Paper arXiv cs.AI 16 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
Evaluating the Robustness of PRNU Source-Camera Attribution to the Fingerprint-Copy Attack: An Open Toolkit with Triangle-Test Detection
📄 Paper arXiv cs.CR 16 giờ trước

arXiv:2611.17747v1 Announce Type: new Abstract: Photo-Response Non-Uniformity (PRNU) is the de facto standard trace for sensor-level source-camera attribution, and a high Peak-to-Correlation-Energy (PCE) between a questioned image and a camera reference fingerprint is routinely …

🅲 hạng C
23
AutoAssumption: Searching over Assumptions Discovers ML-Systems Algorithms
📄 Paper arXiv cs.AI 3 ngày trước

arXiv:2611.14844v1 Announce Type: new Abstract: Many advances in ML systems came from breaking an assumption that earlier methods took for granted: speculative decoding dropped the assumption that a model needs one forward pass per token. Yet algorithms rarely state their assump…

🅲 hạng C
23
VRMaaS: Verifiable Reward-Model-as-a-Service for Trustworthy LLM Alignment
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.14984v1 Announce Type: new Abstract: Reward models (RMs) are increasingly deployed as service components in LLM alignment pipelines, where payment, audit, moderation, and governance workflows act on the scores they return. An inference proof alone does not show whethe…

🅲 hạng C
21
Stress-Testing Sandbagging Detection Under Adaptive Attack
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.14950v1 Announce Type: new Abstract: Developers, auditors and researchers read evaluation scores as evidence of what a model can do. A model that sandbags, scoring low on purpose while keeping the capability, turns a low score into false reassurance. Sandbagging detec…

🅲 hạng C
20
ProofDiff: Auditable Argument-Level Comparison of AI-Generated Mathematical Proofs
📄 Paper arXiv cs.AI 6 ngày trước

arXiv:2611.10233v1 Announce Type: new Abstract: Mathematical understanding depends on the route from hypotheses to conclusion: how the parts of a proof function and which dependencies carry the argument forward. This structure can persist when wording or notation changes, while …

🅲 hạng C
20
Beyond Prompt Attacks: Least-Action Auditing of Concept Erasure
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.10106v1 Announce Type: new Abstract: Concept erasure, or concept unlearning, in text-to-image diffusion models is usually audited with prompt attacks. A prompt attack tests whether one conditioning string still retrieves the erased concept. It does not measure the pro…

🅲 hạng C