conftrace_

adversarial attack

1621 papers

Explore in graph

Also known as

AA

Co-occurring keywords

adversarial robustness (1341) adversarial example (564) black-box attack (237) large language model (13587) neural network (6616) adversarial learning (1595) adversarial defense (325) model robustness (480) adversarial training (1262) adversarial perturbation (384)

Papers

StyleBreak: Revealing Alignment Vulnerabilities in Large Audio-Language Models via Style-Aware Audio Jailbreak AAAI 2026

Semantics-Preserving Adversarial Attacks on Event-Driven Stock Prediction Models AAAI 2026

Rethinking Target Label Conditioning in Adversarial Attacks: A 2D Tensor-Guided Generative Approach AAAI 2026

QRShield: Exploiting Vulnerabilities of Latent Diffusion Models for Preventing AI Art Plagiarism AAAI 2026

Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization AAAI 2026

MOBA: A Material-Oriented Backdoor Attack Against LiDAR-Based 3D Object Detection Systems AAAI 2026

Potent but Stealthy: Rethink Profile Pollution Against Sequential Recommendation via Bi-Level Constrained Reinforcement Paradigm AAAI 2026

Reason2Attack: Jailbreaking Text-to-Image Models via LLM Reasoning AAAI 2026

From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledge AAAI 2026

Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS AAAI 2026

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

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

AEON: Adaptive Embedding Optimized Noise for Robust Watermarking in Diffusion Models WACV 2026

BAFLE-DCT: Bypassing Adversarial Filters via Frequency-Selective Embedding in the DCT Domain WACV 2026

Jailbreaks as Inference-Time Alignment: A Framework for Understanding Safety Failures in LLMs EACL 2026

Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models EACL 2026

Hacking Neural Evaluation Metrics with Single Hub Text EACL 2026

SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning EACL 2026

Transferable Hypergraph Attack via Injecting Nodes into Pivotal Hyperedges AAAI 2026

Poisoned Distillation: Injecting Backdoors into Distilled Datasets Without Raw Data Access AAAI 2026

Spatial-Spectral Homogeneous Attacks on Physical-World Large Vision-Language Models AAAI 2026

LORETTA: A Low Resource Framework to Poison Continuous Time Dynamic Graphs AAAI 2026

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

Improving the Convergence Rate of Ray Search Optimization for Query-Efficient Hard-Label Attacks AAAI 2026

In-Context Representation Hijacking ACL 2026