conftrace_

Artificial Intelligence › Core AI ›

Adversarial Learning

1,292 papers

Papers per year

1

1

1

1

1

1

7

35

86

130

166

188

166

185

264

59

'10

'20

'25

Papers

Mitigating Backdoor Attacks via Trigger Reconstruction and Model Hardening WACV 2026

Unnoticed Yet Effective: A Hybrid Physical Camouflage Framework Against DNNs and Human Perception AAAI 2026

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

CodeHacker: Automated Test Case Generation for Detecting Vulnerabilities in Competitive Programming Solutions ACL 2026

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning ACL 2026

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

ROSE: An Intent-Centered Evaluation Metric for NL2SQL ACL 2026

Compete to Complete: Co-opetition Adversarial Learning for Retrieval-Augmented Generation ACL 2026

StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation ACL 2026

Calibrating Inference Time Alignment with Sequence-level Risk Accumulation ACL 2026

Enhancing the Transferability of Jailbreak Attacks on Large Language Models via Exploiting Reparameterization Invariance ACL 2026

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

Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token Optimization ACL 2026

Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models ACL 2026

DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs ACL 2026

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

HarmRLVR: Weaponizing Verifiable Rewards for Harmful LLM Alignment ACL 2026

Fingerprinting LLMs via Prompt Injection ACL 2026

Locket: Robust Feature-Locking Technique for Language Models ACL 2026

PARASITE: Conditional System Prompt Poisoning to Hijack LLMs ACL 2026

Query-Efficient Agentic Graph Extraction Attacks on GraphRAG Systems ACL 2026

In-Context Representation Hijacking ACL 2026

Activation-Guided Local Editing for Jailbreaking Attacks ACL 2026

Reference Attack: A New Cross-Modal Jailbreaking Attack against Multimodal Large Language Models ACL 2026

Seeing No Evil: Blinding Large Vision-Language Models to Safety Instructions via Adversarial Attention Hijacking ACL 2026