The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections Paper • 2510.09023 • Published Oct 10, 2025 • 10
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities Paper • 2507.06261 • Published Jul 7, 2025 • 64
Cascading Adversarial Bias from Injection to Distillation in Language Models Paper • 2505.24842 • Published May 30, 2025 • 6
Lessons from Defending Gemini Against Indirect Prompt Injections Paper • 2505.14534 • Published May 20, 2025 • 8
Fixing 7,400 Bugs for 1$: Cheap Crash-Site Program Repair Paper • 2505.13103 • Published May 19, 2025 • 6
Operationalizing Contextual Integrity in Privacy-Conscious Assistants Paper • 2408.02373 • Published Aug 5, 2024 • 5
