Alert button
Picture for Daniel Kang

Daniel Kang

Alert button

LLM Agents can Autonomously Hack Websites

Feb 16, 2024
Richard Fang, Rohan Bindu, Akul Gupta, Qiusi Zhan, Daniel Kang

Viaarxiv icon

Removing RLHF Protections in GPT-4 via Fine-Tuning

Nov 10, 2023
Qiusi Zhan, Richard Fang, Rohan Bindu, Akul Gupta, Tatsunori Hashimoto, Daniel Kang

Figure 1 for Removing RLHF Protections in GPT-4 via Fine-Tuning
Figure 2 for Removing RLHF Protections in GPT-4 via Fine-Tuning
Viaarxiv icon

Identifying and Mitigating the Security Risks of Generative AI

Aug 28, 2023
Clark Barrett, Brad Boyd, Ellie Burzstein, Nicholas Carlini, Brad Chen, Jihye Choi, Amrita Roy Chowdhury, Mihai Christodorescu, Anupam Datta, Soheil Feizi, Kathleen Fisher, Tatsunori Hashimoto, Dan Hendrycks, Somesh Jha, Daniel Kang, Florian Kerschbaum, Eric Mitchell, John Mitchell, Zulfikar Ramzan, Khawaja Shams, Dawn Song, Ankur Taly, Diyi Yang

Figure 1 for Identifying and Mitigating the Security Risks of Generative AI
Viaarxiv icon

Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Feb 11, 2023
Daniel Kang, Xuechen Li, Ion Stoica, Carlos Guestrin, Matei Zaharia, Tatsunori Hashimoto

Figure 1 for Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks
Figure 2 for Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks
Figure 3 for Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks
Figure 4 for Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks
Viaarxiv icon

Q-Diffusion: Quantizing Diffusion Models

Feb 10, 2023
Xiuyu Li, Long Lian, Yijiang Liu, Huanrui Yang, Zhen Dong, Daniel Kang, Shanghang Zhang, Kurt Keutzer

Figure 1 for Q-Diffusion: Quantizing Diffusion Models
Figure 2 for Q-Diffusion: Quantizing Diffusion Models
Figure 3 for Q-Diffusion: Quantizing Diffusion Models
Figure 4 for Q-Diffusion: Quantizing Diffusion Models
Viaarxiv icon

Scaling up Trustless DNN Inference with Zero-Knowledge Proofs

Oct 17, 2022
Daniel Kang, Tatsunori Hashimoto, Ion Stoica, Yi Sun

Figure 1 for Scaling up Trustless DNN Inference with Zero-Knowledge Proofs
Figure 2 for Scaling up Trustless DNN Inference with Zero-Knowledge Proofs
Figure 3 for Scaling up Trustless DNN Inference with Zero-Knowledge Proofs
Figure 4 for Scaling up Trustless DNN Inference with Zero-Knowledge Proofs
Viaarxiv icon

Proof: Accelerating Approximate Aggregation Queries with Expensive Predicates

Jul 28, 2021
Daniel Kang, John Guibas, Peter Bailis, Tatsunori Hashimoto, Yi Sun, Matei Zaharia

Figure 1 for Proof: Accelerating Approximate Aggregation Queries with Expensive Predicates
Viaarxiv icon