TextSeal2: Distortion-Free LLM Watermarking with Copula Mixing and Memoryless Races
We present TextSeal2, a distortion-free watermark for large language models that keeps its signal under speculative deco
#cs.CL
共收录 424 条相关情报。
← 返回所有主题Surprise Alone Learns Lies: Evidence-Gated Continual Learning for LLMs from Streaming Claims
Continual learning methods for large language models increasingly decide what to learn by surprise, keeping the inputs t
ARBITRA: Robust Document-Level ATT&CK Extraction via Multi-Expert Argumentation
Cyber threat intelligence (CTI) reports describe adversary behavior in natural language, but converting them into struct
AgentHeal: Evaluating Goal-Preserving Resource Recovery of Web Agents under Access Barriers
Large language model (LLM) agents have demonstrated strong capabilities in automating complex information-seeking and tr
Manifest-Assisted Retrieval in Artificial Intelligence Search: Evidence Gaps and a Security Evaluation
The external sources retained in our non-systematic audit did not isolate the incremental security or utility effect of
Component Translation and Judge-Labelled Refusal: A Multilingual Safety Evaluation
Whole-prompt translation evaluates a request in different languages but does not compare which component carries a langu
Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness
We introduce Heads of Security (HoS), a prompt injection defense that enforces instruction-data separation via a small s
Agentic Backdoors via Pretraining Poisoning
Large language models are pretrained on vast, uncurated corpora scraped from the public web. This creates a security ris
Watermark Basins: Black-Box Detection of Distilled LLMs
Proprietary language models and their reasoning traces are vulnerable to API-based distillation, where an adversary trai
No Tokenizer, Still a Gap: Cross-Lingual Fairness of Homoglyph and Invisible-Character Watermarking
Homoglyph and invisible-character watermarks are edit-based watermarks. Instead of changing how a model generates text,
Atomic Security Concerns: Towards a Foundational Language for Security Knowledge Representation
Cybersecurity governance, risk management, compliance, and security architecture rely on numerous concepts, including se
CoSA: The Conflict of Skills Attack in Real-World LLM Agent Ecosystems
Agent Skills allow LLM agents to combine reusable capabilities, but checking each Skill in isolation cannot rule out pol
Does the Voynich Manuscript Mean Anything? Calibrated Tests Find Little Trace of Language
The Voynich manuscript is a fifteenth-century book in a script that no one can read. One account holds that its text mea
Factual Yet One-Sided: Stance Poisoning and Evidence Balancing in Retrieval-Augmented Generation
The stance expressed in responses from retrieval-augmented generation systems is significantly influenced by the stance
Reversible Pseudonymisation of Documents Sent to External LLMs: an Open Bilingual Benchmark and an Engine
Professionals send working documents to external large language models. A common safeguard is reversible pseudonymisatio
Ranking Is Not Deciding: Benchmark Shortcuts and Operating-Point Collapse in Query-Time RAG Poisoning Defenses
Query-time filters that screen each retrieved document before it reaches the generator are the dominant published defens
EdgeDeID: A 0.6B Clinical De-identifier Trained Without Real Patient Data
De-identifying clinical notes with a hosted language model discloses the information the step is meant to protect. We pr
Depth-Dependent Safety Geometry in Vision-Language Models: Layer-Wise Localization and Bidirectional Refusal Control
Vision-Language Models (VLMs) are widely deployed, yet the internal mechanisms behind their safety behavior remain poorl
AfterDeleteBench: Auditing Post-Deletion Information Persistence in LLM Agents
Many LLM agents maintain external persistent memory and derive additional state from past interactions, such as summarie
Scaling Laws for Safety Probes
Safety probes trained on a model's activations are a standard tool for monitoring language models in real time. Each tim