SEAL: Sealed Queries for Local Sanitization against Indirect Prompt Injection
Indirect prompt injection threatens local LLM agents through untrusted tool outputs, motivating defenses that suppress a
2026-10-31 归档
今日共收录 3279 条安全情报，包含 2996 个 CVE，94 篇安全通告，以及 100 篇研究论文。
← 返回归档列表Systematic Evaluation of Adversarial Jailbreaking Attacks and Defenses Across Seven Large Language Models
Large language models (LLMs) deployed in safety-critical settings must resist adversarial inputs designed to elicit harm
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
REALM: Identifying Minimal Task Assets for LLM Agents
Large language model (LLM) agents often receive access to more files, accounts, and services than a task requires. Promp
Session-Bound Behavioral Watermarking for Autonomous LLM Agents
Large Language Model (LLM) agents are increasingly acting through Web interfaces and external tools. They produce trajec
WebMaze: Defending Against LLM-Powered Web Scanners with Functionality-Coupled Deception
Large language models (LLMs) have enabled more effective vulnerability scanning of web applications. However, these capa
GI-RTL-Fuzz: Grammar-Informed RTL Generation with LLMs for End-to-End Differential Simulator Fuzzing
Register-Transfer Level (RTL) simulators are fundamental to modern IC design workflows, yet like any complex software, t
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
Is it my preference? Role Grounding Attack against Agent's Memory via Social Interaction
LLM-based agents now share experiences on social platforms and remember new preferences to enhance their performance. Ho
Zero Trust-Enabled Adaptive Incident Response using Hierarchical Reinforcement Learning
Modern enterprises increasingly operate through complex information systems (IS) enabled by cloud computing, remote and
Jailbreak Connectivity: Towards Diverse, Transferable, and Universal Multimodal Large Language Model Jailbreak
Multimodal large language models (MLLMs) are vulnerable to visual jailbreak attacks that bypass safety safeguards. Exist
Understanding Post-Quantum Cryptography Adoption: Practices, Challenges, and Evolution in Open-Source Software
Post-quantum cryptography (PQC) standards establish algorithms for quantum-safe systems, but empirical evidence about ho
Scan Before You Install: Detecting and Mitigating Local and Composite Vulnerabilities in Skills
An agent skill packages natural-language instructions, scripts, and reference files that an LLM-based agent loads for a
Structured Security Explanations for Learning-Based Vulnerability Detection
Software vulnerability detection remains difficult because existing approaches rely on predefined analysis rules, learn
Agentic Backdoors via Pretraining Poisoning
Large language models are pretrained on vast, uncurated corpora scraped from the public web. This creates a security ris
The Envelope Layer: An Underestimated Surface of LLM Agent Defense
Prior work framed the envelope layer as the channel through which malicious content enters an agent, and established it
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
When Skills Tell Agents Not to Ask: A Large-Scale Study of Oversight Directives in Agent Skills
Agent skills, reusable instruction packages centred on a SKILL.md file, extend AI agents on demand, and a single line in
Blindfold: Keeping the Audit Coin Secret from LLM Agents
Audit-based certification bounds the violation rate of an LLM agent by auditing a random fraction $\varepsilon$ of actio