uiuc-backdoor-attack

uiuc-backdoor-attack's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

qiusizhan 

authored 6 papers 6 days ago

Removing RLHF Protections in GPT-4 via Fine-Tuning

Paper • 2311.05553 • Published Nov 9, 2023

LLM Agents can Autonomously Hack Websites

Paper • 2402.06664 • Published Feb 6, 2024 • 3

ConFiguRe: Exploring Discourse-level Chinese Figures of Speech

Paper • 2209.07678 • Published Sep 16, 2022

Teams of LLM Agents can Exploit Zero-Day Vulnerabilities

Paper • 2406.01637 • Published Jun 2, 2024 • 2

InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents

Paper • 2403.02691 • Published Mar 5, 2024

Visual Backdoor Attacks on MLLM Embodied Decision Making via Contrastive Trigger Learning

Paper • 2510.27623 • Published 9 days ago • 12

Hanyang81 

authored a paper 26 days ago

ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning

Paper • 2510.12693 • Published 26 days ago • 26

Hanyang81 

authored a paper 9 months ago

EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents

Paper • 2502.09560 • Published Feb 13 • 35