Similar Items: Persona-Conditioned Adversarial Prompting: Multi-Identity Red-Teaming for Adversarial Discovery and Mitigation
- Autonomous Adversary: Red-Teaming in the age of LLM
- Backdoor Mitigation in Object Detection via Adversarial Fine-Tuning
- Detecting Adversarial Data via Provable Adversarial Noise Amplification
- FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption
- IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection
- Low Rank Adaptation for Adversarial Perturbation