AI Threat AlertBeyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces
Jailbreak attacks remain a critical threat to the safe deployment
SafeSpec: Fast and Safe LLM via Dynamic Reflective Sampling
Speculative inference accelerates large language model (LLM) decoding but provides no inherent safety guarantees. Existing safety defenses are largely incompatible with speculative inference: they either introduce additional computation or disrupt
OCELOT: Inference-Leakage Budgets for Privacy-Preserving LLM Agents
Large language model (LLM) agents increasingly act on a user
Differential Harm Propensity in Personalized LLM Agents: The Curious Case of Mental Health Disclosure
Large language models (LLMs) are increasingly deployed as tool-using
Bits Leaked per Query: Information-Theoretic Bounds on Adversarial Attacks against LLMs
Adversarial attacks by malicious users that threaten the safety of
A Multilingual, Large-Scale Study of the Interplay between LLM Safeguards, Personalisation, and Disinformation
Large Language Models (LLMs) can generate human-like disinformation, yet
Fewer Weights, More Problems: A Practical Attack on LLM Pruning
pruning remain underexplored. In this work, for the first time, we show that modern LLM pruning methods can be maliciously exploited. In particular, an adversary can construct a model that
The Rogue Scalpel: Activation Steering Compromises LLM Safety
Activation steering is a promising technique for controlling LLM behavior by adding semantically meaningful vectors directly into a model's hidden states during inference. It is often framed
Beyond Sharp Minima: Robust LLM Unlearning via Feedback-Guided Multi-Point Optimization
Current LLM unlearning methods face a critical security vulnerability that
Secure Speculative Decoding for Large Language Models
Speculative decoding accelerates inference for a large language model (LLM), referred to as the \emph{target model}, by first using a smaller model, referred to as the \emph{draft model
Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures
Detectors of alignment failures screen deployed language models and score
Towards Automated Cyber Threat Intelligence Elicitation in Underground Forums
this paper presents DarkBot, to the best of our knowledge, the first multi-agent LLM-based system for active CTI elicitation in underground forums. DarkBot decomposes the interaction task across
Harnessing Textual Refusal Directions for Multimodal Safety
relax this constraint and investigate whether textual refusal directions, extracted directly from the LLM backbone, generalize across modalities (i.e., image, video). Preliminary findings confirm this ability, though effectiveness is conditioned
An Empirical Study of Privacy Leakage Chains via Prompt Injection in Black-Box Chatbot Environments
LLM-based chatbot agents increasingly process user requests by combining
Transient Turn Injection: Exposing Stateless Multi-Turn Vulnerabilities in Large Language Models
policy enforcement in both commercial and open-source LLMs, marking a departure from conventional jailbreak approaches that typically depend on maintaining persistent conversational context. Our extensive evaluation across state
SFCoT: Safer Chain-of-Thought via Active Safety Evaluation and Calibration
have demonstrated remarkable capabilities in complex reasoning tasks. However, they remain highly susceptible to jailbreak attacks that undermine their safety alignment. Existing defense mechanisms typically rely on post hoc filtering
DeepContext: Stateful Real-Time Detection of Multi-Turn Adversarial Intent Drift in LLMs
While Large Language Model (LLM) capabilities have scaled, safety guardrails remain largely stateless, treating multi-turn dialogues as a series of disconnected events. This lack of temporal awareness facilitates
TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering
As increasingly capable open-weight large language models (LLMs) are
Trust The Typical
Current approaches to LLM safety fundamentally rely on a brittle cat-and-mouse game of identifying and blocking known threats via guardrails. We argue for a fresh approach: robust safety
Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N Sampling
propose a scaling-aware Best-of-N estimation of risk, SABER, for modeling jailbreak vulnerability under Best-of-N sampling. We model sample-level success probabilities using a Beta distribution