cập nhật 46 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5436, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

23
Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions
📄 Paper HF Daily Papers 23 ngày trước

When an LLM group's discussion is compressed into a short memory for a final decision maker, what should the memory keep? Two natural heuristics keep the rarest claims or the claims relevant to the decision criteria. On hidden-profile tasks both look attractive, because how widel…

🅲 hạng C
23
AI-Generated Non-Consensual Intimate Imagery is Configured, Not Built: How General-Purpose AI Technology Enables Sexual Violence
📄 Paper arXiv cs.CR 20 ngày trước

arXiv:2610.37949v1 Announce Type: new Abstract: AI-generated non-consensual intimate imagery (AIG-NCII) is an increasingly prevalent form of online abuse, distinguished from AI-generated sexual content (AIG-SC) by the sexualized depiction of a real person's identity without thei…

🅲 hạng C
23
REALM: Identifying Minimal Task Assets for LLM Agents
📄 Paper arXiv cs.CR 20 ngày trước

arXiv:2610.39155v1 Announce Type: new Abstract: Large language model (LLM) agents often receive access to more files, accounts, and services than a task requires. Prompt injection turns this excess access into an opportunity to redirect execution toward unrelated resources. Appl…

🅲 hạng C
23
Can Personal Requirements Become Supervision for Planning?
📄 Paper arXiv cs.AI 17 ngày trước

arXiv:2610.40992v1 Announce Type: new Abstract: Managing multiple chronic conditions through diet requires satisfying disease- and medication-specific requirements jointly across meals and days while preserving established eating habits. These requirements are public in clinical…

🅲 hạng C
23
LLM Detoxification via Transition-Aware Reward-Guided Representation Sampling
📄 Paper arXiv cs.AI 17 ngày trước

arXiv:2610.41165v1 Announce Type: new Abstract: Large Language Models (LLMs) can generate toxic content, motivating effective test-time detoxification. Existing representation steering methods often rely on static or coarse interventions and provide imprecise guidance because th…

🅲 hạng C
23
TRIDENT and SHAKTI: A Framework and Benchmark for Hindi AI-Text Detection
📄 Paper arXiv cs.AI 17 ngày trước

arXiv:2610.41232v1 Announce Type: new Abstract: As Large Language Models (LLMs) become increasingly multilingual, distinguishing human-written from AI-generated text is essential for maintaining information integrity. However, research remains English-centric, with limited bench…

🅲 hạng C
23
Evaluating Structural and SAT Attack Resilience in Cryptographic Dynamic Logic Locking via Keystream Capping
📄 Paper arXiv cs.CR 17 ngày trước

arXiv:2610.41083v1 Announce Type: new Abstract: Untrusted third-party entities throughout the semiconductor supply chain expose proprietary hardware intellectual property to reverse engineering, piracy, and overproduction. While logic locking counters this threat by embedding ke…

🅲 hạng C
👁 Trúng danh sách theo dõi: kw:supply chain
23
Simple Features Beat Most AI Control Monitors
📄 Paper arXiv cs.CR 17 ngày trước

arXiv:2610.41713v1 Announce Type: new Abstract: AI control relies on monitors to catch a capable model that sabotages its work. These monitors are evaluated on their ability to differentiate honest from backdoored code. We show that on a standard evaluation dataset, simple featu…

🅲 hạng C
23
Dependence-Aware Risk Assessment and Optimal Design of AI-Agent Safeguard Systems
📄 Paper arXiv cs.AI 16 ngày trước

arXiv:2611.00386v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on safeguards to prevent unauthorized actions while preserving legitimate service. However, existing risk assessments often focus on individual safeguard performance while overloo…

🅲 hạng C
23
Skill++: Towards Lifelong Agents via Routing-Aware Skill Refinement
📄 Paper arXiv cs.AI 16 ngày trước

arXiv:2611.00544v1 Announce Type: new Abstract: Large language model (LLM) agents extend their capabilities with skills, each with a name, a description, and a body. Under progressive disclosure, an LLM router selects skills by name and description alone and loads only the selec…

🅲 hạng C
23
WAR-CRAFT: Refining Web API Recommendations through Requirement Auditing
📄 Paper arXiv cs.AI 16 ngày trước

arXiv:2611.00564v1 Announce Type: new Abstract: Web API recommenders return a set of APIs for a mashup request but do not check it against provider documentation, the main public evidence of an API's capabilities. The set can therefore contain unsupported or redundant APIs and m…

🅲 hạng C
23
E-UDE: A Scientific Machine Learning Model for Malware Propagation Dynamics
📄 Paper arXiv cs.CR 16 ngày trước

arXiv:2611.00971v1 Announce Type: new Abstract: Understanding the malware propagation dynamics over the Internet is crucial for effectively controlling its spread. Existing mechanistic and data-driven models in the context of malware propagation dynamics, have some issues with e…

🅲 hạng C
23
Enhancing Edge AI System Security with a Stacked Hardware Security Controller for Robust and Energy-Efficient Anomaly Detectio
📄 Paper arXiv cs.CR 16 ngày trước

arXiv:2611.01150v1 Announce Type: new Abstract: In recent years, the growing adoption of Edge AI systems has been accompanied by a surge in security threats. Edge AI deployments face an rapidly evolving spectrum of security threats, from side-channel information leakage to ad- v…

🅲 hạng C
23
A Security Analysis of Verifiable Credential Verification Pipelines: Attack Surface Arising from JSON-LD/RDFC Canonicalization Compared with SD-JWT VC and mdoc
📄 Paper arXiv cs.CR 15 ngày trước

arXiv:2611.04461v1 Announce Type: new Abstract: We evaluate, at implementation level and under an explicit threat model, the verification pipelines of three Verifiable Credential (VC) formats: SD-JWT VC; the W3C Verifiable Credentials Data Model 2.0 with the Data Integrity crypt…

🅲 hạng C