← Core AI
Artificial Intelligence › Core AI ›

Adversarial Learning

1235 directly classified papers

Papers per year

Papers

Bias in the Mirror : Are LLMs opinions robust to their own adversarial attacks ACL 2025
TombRaider: Entering the Vault of History to Jailbreak Large Language Models EMNLP 2025
RP-PGD: Boosting Segmentation Robustness with a Region-and-Prototype Based Adversarial Attack AAAI 2025
VisCRA: A Visual Chain Reasoning Attack for Jailbreaking Multimodal Large Language Models EMNLP 2025
Attacking Vision-Language Computer Agents via Pop-ups ACL 2025
Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors EMNLP 2025
Towards Robust Defense against Customization via Protective Perturbation Resistant to Diffusion-based Purification ICCV 2025
Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection EMNLP 2025
AGD: Adversarial Game Defense Against Jailbreak Attacks in Large Language Models ACL 2025
SUA: Stealthy Multimodal Large Language Model Unlearning Attack EMNLP 2025
PoolAtnRes: Towards Generalisable Differential Morphing Attack Detection WACV 2025
RedHerring Attack: Testing the Reliability of Attack Detection EMNLP 2025
When Visual State Space Model Meets Backdoor Attacks WACV 2025
SPIRIT: Patching Speech Language Models against Jailbreak Attacks EMNLP 2025
NullSwap: Proactive Identity Cloaking Against Deepfake Face Swapping ICCV 2025
Jailbreak LLMs through Internal Stance Manipulation EMNLP 2025
Adversarial Training for Probabilistic Robustness ICCV 2025
AIP: Subverting Retrieval-Augmented Generation via Adversarial Instructional Prompt EMNLP 2025
Integrating Argumentation Features for Enhanced Propaganda Detection in Arabic Narratives on the Israeli War on Gaza COLING 2025
SABER: Uncovering Vulnerabilities in Safety Alignment via Cross-Layer Residual Connection EMNLP 2025
SilverSpeak: Evading AI-Generated Text Detectors using Homoglyphs COLING 2025
Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time EMNLP 2025
PBCAT: Patch-Based Composite Adversarial Training against Physically Realizable Attacks on Object Detection ICCV 2025
TrojanWave: Exploiting Prompt Learning for Stealthy Backdoor Attacks on Large Audio-Language Models EMNLP 2025
InfAL: Inference Time Adversarial Learning for Improving Research Ideation EMNLP 2025