Defending Against Dormant Poisoning Attacks Across Language and Multimodal Agents
Recent work shows that attackers can implant dormant malicious behaviors that remain hidden at release but emerge after
#cs.CL
共收录 424 条相关情报。
← 返回所有主题The Window Is in the Reasoning: When LLM Agents Decide to Follow Prompt Injections
LLM agents that read untrusted content can be hijacked by prompt injections. Runtime monitors that try to catch a hijack
Ignored, Not Refused: What Low Prompt-Injection Success Rates Hide in Small Tool-Using Agents
Tool-using agents read untrusted external content, which exposes them to indirect prompt injection (IPI), where hidden i
ECHO: Replacing the Compliance Proxy with Response Harmfulness in Optimization-Based Jailbreak Attack
Despite extensive safety alignment, large language models remain vulnerable to jailbreak attacks. Existing optimization-
SAFE-Mem: Secure Agentic Memory with Fine-Grained Authority and Governance-Aware Retrieval
Large language model (LLM) agents increasingly rely on persistent memory to support long-term reasoning and personalized
Identify, Classify, Act: Per-Instruction Controlled Compliance for LLMs over External Data
LLMs over external data face a per-instruction tension: a single document or tool return often interleaves legitimate di
Watermarkability: Measuring and Improving Language-Model Compatibility with Logit-Based Watermarks
Language-model watermarks can help identify model-generated text, encode provenance information, and detect post-generat
Veil-Then-Reveal: Protecting PII Privacy via Reversible Pseudo-Anonymization in Zero-Trust User--LLM Interaction
Large language models (LLMs) increasingly process sensitive documents and personal information, yet sending prompts cont
Exploring The Empirical Privacy Landscape of Synthetic Data
Methods for training language models on sensitive data differ in how they balance capability gains against the risk of l
Broad and Efficient PII Detection with Unified Labels
Personally Identifiable Information (PII) detection models must efficiently find identifiers across diverse contexts whi
Language Is a Security Surface for Agent Guards
Step-level guards decide, before each tool call, whether an agent's next action is safe given the user's request and the
QuasiLeak-Bench: Evaluating LLM-Based Privacy Detectors on Policy-Conditioned Quasi-Evidence Group Recovery
Natural language messages often contain quasi-identifiers that are weak in isolation but can jointly reveal an individua
CARE-SD: Explainable Reasoning Architecture for Local SLM Self-Disclosure Analysis in Textual Data
Cybersecurity interviews uncover critical security experiences, behaviors, and privacy concerns often not fully captured
SHIP: Structured and Hierarchical Insight with Privacy
Extracting insights from textual data while protecting user privacy is increasingly important. Existing methods produce
CascadeLedger: Counterfactual Auditing of Information and Resource Integrity in LLM Cascades
We introduce CascadeLedger, a counterfactual execution-audit framework for budgeted language-model cascades. The protoco
Pin It on Anyone: Certified Targeted Displacement of Multi-Bit LLM Watermarks Without the Key
Multi-bit watermarking embeds a message, typically an account identifier, into LLM output so that harmful text can be tr
Jev-Guard: Fast Routing and Auditing Agent Actions over Editable Policy Trees
Agent harnesses require a low-latency guardrail model together with customizable audit policies. However, deploying an a
Encrypted Skills Can Become New Security Exploits If AI Agents Know How to Decipher
Third-party skills can expose LLM agents to malicious instructions hidden by encoding. We introduce Ciphered Skill Injec
SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models
Agent skills turn natural-language instructions into actions, creating a security challenge: legitimate automation and m
Differential Privacy Protected Preference Alignment on Survey Derived Data
Preference alignment enables language models to better reflect human values, but the preference data contains sensitive