DP-ES: Differentially Private Evolution Strategies for Prompt Optimization
Token-level differentially private (DP) prompt optimization methods such as DP-OPT can become unstable under tight priva
2026-10-06 归档
今日共收录 1258 条安全情报，包含 460 个 CVE，421 篇安全通告，以及 100 篇研究论文。
← 返回归档列表Where Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability Repair
Localizing where an LLM-based agent first fails to uphold security during a repair can show which stage of its workflow
Cross-Lingual Transferability of Training Data Extraction Attacks to Recover Memorized PII
The robustness of Personally Identifiable Information (PII) protection in Large Language Models (LLMs) is a critical con
Backdooring Sparse Autoencoders
Sparse autoencoders (SAEs) are increasingly used not only to interpret language models but also to intervene on their in
Compromise Is Not Consequence: Evaluating Task-Scoped Authorization in LLM Agents with Paired Replay
A tool-using model can follow a malicious instruction even when its credentials are valid. We study whether task-scoped
AgentDoxx: Agentic Re-identification of Anonymized Text with Web Search
As Large Language Models (LLMs) gain tool use capabilities such as web search, they can retrieve and cross-reference pub
Don't Judge an LLM Only by Its Activations: Discovering Suppressed Safety Features via Counterfactual Activation Potential
Mechanistic interpretability has emerged as the primary means to understand safety behavior of LLMs. However, existing t
AutoDP-LLM: Automating Data Pre-processing for Intrusion Detection Systems using Large Language Models
The increasing complexity and scale of modern cyber-attacks demand intelligent and computationally efficient Intrusion D
Reflections and Fragments: Securing LLMs Against Sequential Mosaic Attacks
Self-play red-teaming improves language-model safety by pitting attacker and defender roles against each other in a zero
Grammar-Guided Code Watermarking with Green Temperature
Large language model watermarking embeds detectable statistical signals during decoding, but the resulting changes to to
Red-TTT: Test-Time Training for Automated Jailbreaking Large Language Models
Large language models remain vulnerable to jailbreaks, and automated red teaming is the standard way to find jailbreaks
Invisible Ink, Visible Lies: How Production Watermarking Causes LLMs to Hallucinate
Text watermarking helps identify AI-generated content, but its effect on factual reliability remains underexplored. In t
Forecasting Cybersecurity Incidents Using Geopolitical Data and Large Language Models
Predicting security incidents is a profound task critical for informing proactive defensive measures and cyber-insurance
Not Self-Decidable: LLMs Cannot Draw the Boundary of What an Agent Verifier Can Check
A verifier for an agent faces rules of two kinds: the ones a fixed check can settle and the ones that require a judge. A
Reactivating Alignment: Defending LLMs from Jailbreaks via Intention-Aware Input-Output Matching
Large language models (LLMs) remain vulnerable to jailbreak attacks that conceal harmful intent within complex adversari
COPEX: Benchmarking LLM Robustness to Adversarial Context Across Model Context Protocol Layers
Large language models increasingly mediate tool use in Model Context Protocol (MCP) systems, where adversarial influence
Self-Reflection Fine-Tuning: Enhancing Agent Security against Prompt Injection Attacks from Failure Experience
Large language model (LLM) agents are increasingly deployed in tool-augmented environments, but their reliance on extern
Language Model Fingerprinting Requires Rethinking Watermark Teachers
LLM fingerprinting via watermark distillation embeds a statistical watermark signal into model weights, enabling model o
Adaptive Co-Serving LLM Watermarking on Modern Inference Engines
Large language model (LLM) watermarking is important for ownership verification and intellectual property protection. Ho
Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks
Security benchmarks for LLM-based agents often report the attack success rate (ASR) as a measure of model robustness and