Jie Zhang

PhD student, Department of Computer Science, ETHZ - ETH Zurich

Joined

May 2021

Names

Jie Zhang (Preferred)

Emails

****@zju.edu.cn (Confirmed)

****@inf.ethz.ch (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

PhD student

Department of Computer Science, ETHZ - ETH Zurich (inf.ethz.ch)

2023 – 2027

MS student

Zhejiang University (zju.edu.cn)

2020 – 2023

Advisors, Relations & Conflicts

PhD Advisor

Florian Tramer

Present

Expertise

Federated Learning

Present

Adversarial examples

Present

AI security & privacy

Present

Publications

Black-box Optimization of LLM Outputs by Asking for Directions
Jie Zhang, Meng Ding, Yang Liu, Jue Hong, Florian Tramèr
- ICLR 2026 Trustworthy AI
- Readers: Everyone
Black-box Optimization of LLM Outputs by Asking for Directions
Jie Zhang, Meng Ding, Yang Liu, Jue Hong, Florian Tramèr
- Submitted to ICLR 2026
- Readers: Everyone
RealMath: A Continuous Benchmark for Evaluating Language Models on Research-Level Mathematics
Jie Zhang, Cezara Petrui, Kristina Nikolić, Florian Tramèr
- AI4Math@ICML25 Poster
- Readers: Everyone
RealMath: A Continuous Benchmark for Evaluating Language Models on Research-Level Mathematics
Jie Zhang, Cezara Petrui, Kristina Nikolić, Florian Tramèr
- NeurIPS 2025 Datasets and Benchmarks Track poster
- Readers: Everyone
Position: Adversarial ML for LLMs Is Not Making Any Progress
Javier Rando, Jie Zhang, Nicholas Carlini, Florian Tramèr
- Submitted to NeurIPS 2025 Position Paper Track
- Readers: Everyone
The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
Kristina Nikolić, Luze Sun, Jie Zhang, Florian Tramèr
- BuildingTrust
- Readers: Everyone
Blind Baselines Beat Membership Inference Attacks for Foundation Models
Debeshee Das, Jie Zhang, Florian Tramèr
- ICLR 2025 Workshop Data Problems Poster
- Readers: Everyone
Textual Unlearning Gives a False Sense of Unlearning
Jiacheng Du, Zhibo Wang, Jie Zhang, Xiaoyi Pang, Jiahui Hu, Kui Ren
- ICML 2025 poster
- Readers: Everyone
The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
Kristina Nikolić, Luze Sun, Jie Zhang, Florian Tramèr
- ICML 2025 spotlightposter
- Readers: Everyone
Prompt-Independent Safe Decoding to Restrain Unsafe Image Generation for Text-to-Image Models against White-Box Adversary
Shengyuan Pang, Jiangyi Deng, Jialin Wu, Yanjiao Chen, Huanlong Zhong, Xinfeng Li, Jie Zhang, Wenyuan Xu
- Submitted to ICLR 2025
- Readers: Everyone

View all 28 publications

Co-Authors

View all 68 co-authors