cập nhật 1 giờ trước

⏱ Độ trễ thật của tab này: trung bình 6.7 giờ sau khi CVE được công bố (n = 5162, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

29
Can You Undo It? Reversibility Classes for AI Agent Actions
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.22075v1 Announce Type: new Abstract: Tool-using AI agents change files, databases, access rights and public information, yet permission to call a tool does not establish whether a mistake can be undone. We present Reversibility Classes, a declared five-level vocabular…

🅲 hạng C
28
Cyber-Physical RSI for AI-RAN: A Case Study
📄 Paper arXiv cs.AI 12 giờ trước

arXiv:2611.25619v1 Announce Type: new Abstract: Learned models for radio access networks (RANs) are often developed using simulation, yet their predictions can shift when exposed to physical propagation conditions, protocol behavior, and equipment implementations. This paper pre…

🅲 hạng C
27
Posterior Matching Distillation
📄 Paper HF Daily Papers 1 ngày trước

Diffusion distillation accelerates image and video generation by compressing a pretrained teacher's iterative sampling process into a few network evaluations. Distribution-based methods achieve this by matching the student's output distribution to the teacher's. This matching is …

🅲 hạng C
25
GUARD: Stabilizing Recursive Self-Improvement with Regret Guidance
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.23476v1 Announce Type: new Abstract: Autonomous AI agents pair a frozen base model with an editable harness of prompts, skills, tool rules, and memory. Recursive self-improvement (RSI) adapts this harness from experience without weight updates, yet self-editing withou…

🅲 hạng C
25
Mitigating fix reversal: Counterfactual constraints for function-level vulnerability detection
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.24489v1 Announce Type: new Abstract: Function-level vulnerability detectors often exhibit fix reversal, assigning a higher vulnerability probability to a fixed version than to its vulnerable counterpart. Fixes usually lengthen functions, and larger length increases ar…

🅲 hạng C
24
ChronoPatch: Black-Box Energy-Latency Attacks on Vision-Language Models
📄 Paper arXiv cs.CR 12 giờ trước

arXiv:2611.26117v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly deployed as generative inference services, where autoregressive decoding makes response length a key determinant of latency and computational cost. This creates an availability risk: a…

🅲 hạng C
23
Attacker Diversity Reduction in Adaptive LLM Red Teaming
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.19680v1 Announce Type: new Abstract: Reinforcement learning can make automated red-teaming more successful while narrowing the attacks it produces. Co-training an attacker and a defender with group-relative policy optimization (GRPO) has been reported to reduce attack…

🅲 hạng C
23
PGPO: Prototype-Guided Progressive Obfuscation for Privacy-Preserving LLM-Enhanced Recommendation
📄 Paper arXiv cs.CR 1 ngày trước cũng có trên: HF Daily Papers

arXiv:2611.23236v1 Announce Type: cross Abstract: LLM-enhanced recommender systems encode item side information into semantic embeddings, but these embeddings may leak sensitive textual attributes through inversion attacks. Existing input-side defenses rely on trusted collection…

🅲 hạng C
23
Co-Sight Harness: Externalized Control Assets and Deterministic Enforcement for Long-Horizon Business Agents
📄 Paper arXiv cs.AI 4 ngày 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
22
Training Language Models for Introspective Oversight
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.23365v1 Announce Type: new Abstract: Language models increasingly exhibit behaviors that are difficult to detect in transcripts, such as reward hacking, deception, and sycophancy. Asking the assistant follow-up questions about its actions is unreliable, since models a…

🅲 hạng C
22
BOS Summary: The First Token Matters
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.23508v1 Announce Type: new Abstract: Large vision-language models (LVLMs) and language models (LLMs) often exhibit attention sinks, whereby particular positions, such as the beginning-of-sequence (BOS) token, receive a disproportionate share of attention. Under standa…

🅲 hạng C
22
Image Watermarking With Memory Across Reissuance
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.23363v1 Announce Type: new Abstract: Publishers often revise and reissue images, yet valid watermarks may persist on superseded releases or unapproved edits. Even a current release can contain regions last authorized at different revisions. We introduce and formalize …

🅲 hạng C
22
Lossless Reversible Watermarking for AIGC with Applications in Authentication
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.23395v1 Announce Type: new Abstract: AIGC watermarking is commonly used for tracing, but it can also support applications such as authentication and tampering detection. We study lossless reversible watermarking, which enables exact recovery of the original watermarke…

🅲 hạng C
22
A-Tag: Cryptographic File Tagging with Enforced Live Human Presence
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.23602v1 Announce Type: new Abstract: The increasing autonomy of software agents and the proliferation of AI-generated content have weakened the reliability of digital actions as evidence of human involvement. Existing mechanisms, such as digital signatures and authent…

🅲 hạng C
22
Erased but Recoverable: On the Fragility of Concept Erasure Under Fine-Tuning
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.24220v1 Announce Type: new Abstract: Existing concept erasure methods for text-to-image diffusion models primarily focus on suppressing target concepts while preserving non-target generation quality. However, in practical applications, open-source diffusion models are…

🅲 hạng C
22
WorldRuler: Interactive World Modeling under Configurable Rules
📄 Paper HF Daily Papers 2 ngày trước

Rules govern how player actions change interactive worlds. Different rules create distinct gameplay experiences within similar scenes and action spaces. For customizable gameplay, generative world models must follow user-defined rules beyond real-world behaviors. However, realizi…

🅲 hạng C
22
WM^MLLM: Turning MLLMs into World Models
📄 Paper HF Daily Papers 2 ngày trước

Video world models keep the world in the context of a generator, so a revisit is synthesized again and earlier edits can drift or disappear. We present WM^MLLM, the first interactive world model built on multimodal large language models (MLLMs), for persistent, editable world gen…

🅲 hạng C
21
KV-LTM: Persistent Per-Session KV Caches as Long-Term Memory for Personal Assistants
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.21998v1 Announce Type: new Abstract: Personal assistants accumulate months of conversations, but today's long-term memory stacks put derivation or selection between a question and its evidence. In a system-level comparison on LongMemEval, two commercial assistants sco…

🅲 hạng C
21
Is 4-Bit Quantization More Than Noise to a Chat Model's Safety Behaviour? Attributing Behavioural Shifts with Matched Perturbations
📄 Paper arXiv cs.CR 2 ngày trước

arXiv:2611.22186v1 Announce Type: new Abstract: Chat models on phones and laptops are usually 4-bit copies of the model that was evaluated, and audits of such copies disagree about what quantization does to refusal. A 4-bit build is one of many weight perturbations of the same s…

🅲 hạng C