Tagged:

3 posts

• Adversarial Attacks on Vision-Language Models: Pixels as Injection Vectors

  Gradient-crafted image perturbations can override VLM safety guardrails, inject attacker-defined instructions, and trigger tool calls in agentic pipelines. A survey of the empirically confirmed attack landscape and practical defenses.

  Jun 30, 2026 adversarial-attacks vision-language-models multimodal prompt-injection ai-safety agentic-ai

• Jailbreak-as-a-Service: The Underground Market for LLM Exploit Techniques

  Mapping the underground economy around LLM exploitation — paid jailbreak APIs, model-specific bypass markets, and the professionalization of AI adversaries.

  Jun 27, 2026 jailbreak threat-intelligence underground-economy llm-security ai-safety adversarial-attacks defender-implications

• Beyond Text: How Simple Perceptual Tricks Break Multimodal AI Safety

  A systematic study of multimodal jailbreaks shows that models with near-perfect text-only safety can be compromised with >75% success rates using basic image and audio transformations — no gradient access required.

  Jun 19, 2026 jailbreak vision-language-models multimodal ai-safety adversarial-attacks red-teaming