Alert button
Picture for Tom Goldstein

Tom Goldstein

Alert button

Benchmarking ChatGPT on Algorithmic Reasoning

Add code
Bookmark button
Alert button
Apr 04, 2024
Sean McLeish, Avi Schwarzschild, Tom Goldstein

Viaarxiv icon

Measuring Style Similarity in Diffusion Models

Add code
Bookmark button
Alert button
Apr 01, 2024
Gowthami Somepalli, Anubhav Gupta, Kamal Gupta, Shramay Palta, Micah Goldblum, Jonas Geiping, Abhinav Shrivastava, Tom Goldstein

Viaarxiv icon

Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models

Add code
Bookmark button
Alert button
Apr 01, 2024
Yuxin Wen, Leo Marchyok, Sanghyun Hong, Jonas Geiping, Tom Goldstein, Nicholas Carlini

Viaarxiv icon

Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion

Add code
Bookmark button
Alert button
Mar 25, 2024
Hossein Souri, Arpit Bansal, Hamid Kazemi, Liam Fowl, Aniruddha Saha, Jonas Geiping, Andrew Gordon Wilson, Rama Chellappa, Tom Goldstein, Micah Goldblum

Viaarxiv icon

What do we learn from inverting CLIP models?

Add code
Bookmark button
Alert button
Mar 05, 2024
Hamid Kazemi, Atoosa Chegini, Jonas Geiping, Soheil Feizi, Tom Goldstein

Figure 1 for What do we learn from inverting CLIP models?
Figure 2 for What do we learn from inverting CLIP models?
Figure 3 for What do we learn from inverting CLIP models?
Figure 4 for What do we learn from inverting CLIP models?
Viaarxiv icon

Coercing LLMs to do and reveal (almost) anything

Add code
Bookmark button
Alert button
Feb 21, 2024
Jonas Geiping, Alex Stein, Manli Shu, Khalid Saifullah, Yuxin Wen, Tom Goldstein

Viaarxiv icon

ODIN: Disentangled Reward Mitigates Hacking in RLHF

Add code
Bookmark button
Alert button
Feb 11, 2024
Lichang Chen, Chen Zhu, Davit Soselia, Jiuhai Chen, Tianyi Zhou, Tom Goldstein, Heng Huang, Mohammad Shoeybi, Bryan Catanzaro

Viaarxiv icon

Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models

Add code
Bookmark button
Alert button
Feb 05, 2024
Yuancheng Xu, Jiarui Yao, Manli Shu, Yanchao Sun, Zichu Wu, Ning Yu, Tom Goldstein, Furong Huang

Viaarxiv icon

Benchmarking the Robustness of Image Watermarks

Add code
Bookmark button
Alert button
Jan 22, 2024
Bang An, Mucong Ding, Tahseen Rabbani, Aakriti Agrawal, Yuancheng Xu, Chenghao Deng, Sicheng Zhu, Abdirisak Mohamed, Yuxin Wen, Tom Goldstein, Furong Huang

Viaarxiv icon

Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text

Add code
Bookmark button
Alert button
Jan 22, 2024
Abhimanyu Hans, Avi Schwarzschild, Valeriia Cherepanova, Hamid Kazemi, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein

Viaarxiv icon