4 papers
SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing
Jiacheng Zhang, Haoyu He, Sen Zhang +5
In real-world applications, guardrails are often expected to identify unsafe user-model interactions according to application-specific safety policies, rather than relying on prede…
From Risk Classification to Action Plan Remediation: A Guardrail Feedback Driven Framework for LLM Agents
Yuhao Sun, Jiacheng Zhang, Shaanan Cohney +3
LLM-based guardrails typically safeguard agents by evaluating proposed actions or inputs before execution, producing safety signals such as binary allow/deny decisions, risk catego…
Sample-Specific Noise Injection For Diffusion-Based Adversarial Purification
Yuhao Sun, Jiacheng Zhang, Zesheng Ye +2
Diffusion-based purification (DBP) methods aim to remove adversarial noise from the input sample by first injecting Gaussian noise through a forward diffusion process, and then rec…
Let's Roll a BiFTA: Bi-refinement for Fine-grained Text-visual Alignment in Vision-Language Models
Yuhao Sun, Chengyi Cai, Jiacheng Zhang +3
Recent research has shown that aligning fine-grained text descriptions with localized image patches can significantly improve the zero-shot performance of pre-trained vision-langua…