conftrace_

Artificial Intelligence › Core AI ›

Security

95 papers

Papers per year

1

2

1

4

4

83

Papers

Efficient Provably Secure Linguistic Steganography via Range Coding ACL 2026

Anchored Sliding Window: Toward Robust and Imperceptible Linguistic Steganography ACL 2026

CachePrune: Teaching LLMs What Not to Follow via KV-Cache Editing ACL 2026

Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection ACL 2026

Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning ACL 2026

Open Schrödinger’s Closed Box: Identifying Retrieval Augmented Generation in API-Accessible Large Language Model Services ACL 2026

Beyond the Final Actor: Modeling the Dual Roles of Creator and Editor for Fine-Grained LLM-Generated Text Detection ACL 2026

Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models ACL 2026

LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation ACL 2026

Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage ACL 2026

QuantileMark: A Message-Symmetric Multi-bit Watermark for LLMs ACL 2026

SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models ACL 2026

Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS ACL 2026

Detecting RAG Extraction Attack via Dual-Path Runtime Integrity Game ACL 2026

MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning ACL 2026

UMMF: Protecting Copyright of Large Vision-Language Models through Unlearning-based Multimodal Memorization Fingerprint ACL 2026

VIGIL: Defending LLM Agents Against Tool-Stream Injection via Verify-Before-Commit ACL 2026

CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning ACL 2026

ACIArena: Toward Unified Evaluation for Agent Cascading Injection ACL 2026

Defenses Against Prompt Attacks Learn Surface Heuristics ACL 2026

Protecting Language Models Against Unauthorized Distillation through Trace Rewriting ACL 2026

XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants ACL 2026

Fingerprinting LLMs via Prompt Injection ACL 2026

From Trust to Compromise: Outcome-Verified LLM Phishing Simulation and Real-Time Defense ACL 2026

AgentMark: Utility-Preserving Behavioral Watermarking for Agents ACL 2026