cập nhật 30 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5441, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

23
A physics-constrained deep reinforcement learning method for autonomous mission planning of Titan deep space probes
📄 Paper arXiv cs.AI 6 ngày trước

arXiv:2611.15389v1 Announce Type: new Abstract: Titan is a compelling target for future deep space exploration, while its extreme Earth-Titan distance and complex environment make continuous ground-in-the-loop planning impractical. Existing planning methods, primarily developed …

🅲 hạng C
23
VRMaaS: Verifiable Reward-Model-as-a-Service for Trustworthy LLM Alignment
📄 Paper arXiv cs.CR 6 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
23
Privacy Leakage from Recurrent State in LLM Inference
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.16048v1 Announce Type: new Abstract: Personalized LLM services place private facts and application instructions into a prompt, then retain representations of that context for later inference. Latent-state LLMs compress part of this history into fixed-size recurrent st…

🅲 hạng C
23
Harnessing Environmental Scatterers for Endogenous Target Covertness in 6G ISAC: A New Paradigm for Sensing Security
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.16110v1 Announce Type: new Abstract: Integrated sensing and communication (ISAC) is a cornerstone of 6G networks, enabling simultaneous data transmission and environmental perception. However, the ubiquitous radiation of sensing waveforms introduces a critical securit…

🅲 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 6 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
Look It Up: Multi-bit LLM Watermarking via Codebook Search
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.16890v1 Announce Type: new Abstract: Attributing short LLM-generated texts to a specific source remains challenging for existing multi-bit watermarking methods, which often require long generations or costly decoding to recover payloads reliably. We propose a codebook…

🅲 hạng C
23
Constrained Decoding: Harmful or Beneficial? Revisiting Its Impact on LLM Performance
📄 Paper HF Daily Papers 24 ngày trước

Constrained decoding guarantees that Large Language Models (LLMs) produce outputs conforming to predefined formats, but is often assumed to inherently degrade reasoning. We examine this assumption through a taxonomy of three constraint types: format constraints, which enforce out…

🅲 hạng C
23
SPEM: Structure-Aware Procedural Memory for Efficient Skill Use in LLM Agents
📄 Paper arXiv cs.AI 29 ngày trước

arXiv:2610.26995v1 Announce Type: new Abstract: LLM-based agents increasingly rely on reusable skills. However, scaling skill libraries makes efficient and accurate skill use difficult. Full skill loading incurs high token and runtime overhead. In contrast, flat semantic retriev…

🅲 hạng C
23
Sparse RL Relaxation for LLM Reasoning
📄 Paper arXiv cs.AI 29 ngày trước

arXiv:2610.27220v1 Announce Type: new Abstract: Recent work has explored continuous representations in place of discrete tokens during Chain-of-Thought (CoT) reasoning, often referred to as soft CoT. This is motivated by the idea that a mixture of token embeddings can represent …

🅲 hạng C
23
When Models Know but Can't Linearly Say: Relational Encoding Limits Linear Vulnerability Classification in Code LLMs
📄 Paper arXiv cs.CR 29 ngày trước

arXiv:2610.27257v1 Announce Type: new Abstract: Large language models can detect vulnerable code, yet the form of vulnerability encoding in their representations remains unclear. We analyze 8 code models spanning 6.7B-15B parameters on C programs using three datasets (DELTASECOM…

🅲 hạng C
23
Make the Adversary Spend More Energy: Generative Deception against Language-Model Attackers in Critical Infrastructure
📄 Paper arXiv cs.CR 29 ngày trước

arXiv:2610.27739v1 Announce Type: new Abstract: Language-model attackers consume computational resources as they explore and interact with a target, creating an opportunity for cyber deception to impose costs. Whether such engagements favor the defender requires measuring both s…

🅲 hạng C
23
To Manipulate or Not: Opinion Dynamics in LLM Interactions
📄 Paper arXiv cs.AI 28 ngày trước

arXiv:2610.28875v1 Announce Type: new Abstract: Large language models increasingly take part in extended conversations where they can both shape and be shaped by another party's views, yet most persuasion research measures only one side of that exchange. We introduce a controlle…

🅲 hạng C
23
Behavior Beyond Text: Evaluating Refusal Transfer Failure in LLM Agents
📄 Paper arXiv cs.AI 28 ngày trước

arXiv:2610.28982v1 Announce Type: new Abstract: While large language models are increasingly deployed as tool-calling agents, their safety evaluations still focus primarily on their ability to refuse harmful requests in text. We investigate whether the refusal behavior in text t…

🅲 hạng C
23
Inheritance as an Admission Test for LLM Prompt Merge Operators
📄 Paper arXiv cs.AI 28 ngày trước

arXiv:2610.29023v1 Announce Type: new Abstract: Large language model (LLM) agents are often improved by iterating until a fixed verifier is done. Once that verifier saturates, the loop has nothing left to climb. We instead score agents against the current population, and a froze…

🅲 hạng C
23
AutoFraming: Synthesizing Dynamic Frames of C Code with LLMs
📄 Paper arXiv cs.AI 28 ngày trước

arXiv:2610.29046v1 Announce Type: new Abstract: Large language models (LLMs) have shown considerable promise in synthesizing formal specifications from source code. However, existing approaches primarily focus on functional contracts and loop invariants, while largely neglecting…

🅲 hạng C
23
Does Every Instance Count Equally? Order Effects in LLM Multi-Instance Processing
📄 Paper arXiv cs.AI 28 ngày trước

arXiv:2610.29057v1 Announce Type: new Abstract: Users increasingly rely on large language models (LLMs) to analyse collections of independent inputs, such as product reviews or social media posts, and return a single aggregated answer. This setting requires multi-instance proces…

🅲 hạng C
23
Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise
📄 Paper arXiv cs.CR 28 ngày trước

arXiv:2610.28810v1 Announce Type: new Abstract: The widespread adoption of generative artificial intelligence in recent years has brought a parallel rise in prompt injection and jailbreak attacks. By embedding malicious instructions, these exploits manipulate language models to …

🅲 hạng C
23
Prompt Injection Through Forensic Evidence: A Taxonomy and Proof of Concept of Anti-Forensic Attacks on LLM-Assisted Digital Investigations
📄 Paper arXiv cs.CR 28 ngày trước

arXiv:2610.29747v1 Announce Type: new Abstract: Large language models (LLMs) are entering digital forensics as examination assistants and autonomous agents. Digital forensics inverts the usual setting for indirect prompt injection: the evidence under analysis is attacker-control…

🅲 hạng C
23
CALLIOPE: Private Insights into AI Use, Without Embeddings
📄 Paper arXiv cs.CR 28 ngày trước

arXiv:2610.28797v1 Announce Type: cross Abstract: We introduce CALLIOPE, a top-down framework for discovering topic hierarchies in large corpora of unstructured data (e.g., LLM conversations), while supporting differential privacy (DP). Unlike traditional and even recent LLM-aug…

🅲 hạng C