Picture for Xinyu Xing

Xinyu Xing

Enhancing Jailbreak Attack Against Large Language Models through Silent Tokens

Add code
May 31, 2024
Viaarxiv icon

RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation

Add code
May 05, 2024
Figure 1 for RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation
Figure 2 for RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation
Figure 3 for RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation
Figure 4 for RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation
Viaarxiv icon

Assessing Prompt Injection Risks in 200+ Custom GPTs

Add code
Nov 20, 2023
Viaarxiv icon

GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Add code
Sep 19, 2023
Figure 1 for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
Figure 2 for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
Figure 3 for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
Figure 4 for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
Viaarxiv icon

BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning

Add code
May 07, 2021
Figure 1 for BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning
Figure 2 for BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning
Figure 3 for BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning
Figure 4 for BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning
Viaarxiv icon

Robust saliency maps with decoy-enhanced saliency score

Add code
Feb 03, 2020
Figure 1 for Robust saliency maps with decoy-enhanced saliency score
Figure 2 for Robust saliency maps with decoy-enhanced saliency score
Figure 3 for Robust saliency maps with decoy-enhanced saliency score
Figure 4 for Robust saliency maps with decoy-enhanced saliency score
Viaarxiv icon

TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems

Add code
Aug 08, 2019
Figure 1 for TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems
Figure 2 for TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems
Figure 3 for TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems
Figure 4 for TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems
Viaarxiv icon

Explaining Deep Learning Models - A Bayesian Non-parametric Approach

Add code
Nov 07, 2018
Figure 1 for Explaining Deep Learning Models - A Bayesian Non-parametric Approach
Figure 2 for Explaining Deep Learning Models - A Bayesian Non-parametric Approach
Figure 3 for Explaining Deep Learning Models - A Bayesian Non-parametric Approach
Figure 4 for Explaining Deep Learning Models - A Bayesian Non-parametric Approach
Viaarxiv icon

A Comparison of Rule Extraction for Different Recurrent Neural Network Models and Grammatical Complexity

Add code
Jan 16, 2018
Figure 1 for A Comparison of Rule Extraction for Different Recurrent Neural Network Models and Grammatical Complexity
Figure 2 for A Comparison of Rule Extraction for Different Recurrent Neural Network Models and Grammatical Complexity
Figure 3 for A Comparison of Rule Extraction for Different Recurrent Neural Network Models and Grammatical Complexity
Figure 4 for A Comparison of Rule Extraction for Different Recurrent Neural Network Models and Grammatical Complexity
Viaarxiv icon

An Empirical Evaluation of Rule Extraction from Recurrent Neural Networks

Add code
Nov 28, 2017
Viaarxiv icon