◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Wenjie Wang

ShanghaiTech University

4 papers hereh-index 7165 citations11 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • last author3

Across the 3 of 4 papers where every author was matched, so the position is known.

fields
  • cs.CL2
  • cs.CR1
  • cs.LG1
affiliations
  • ShanghaiTech University
ORCID 0000-0002-7559-6211
same name
  • Wenjie Wang — 47 papers, h 31
  • Wenjie Wang — 13 papers, h 14
  • Wenjie Wang — 11 papers, h 4
  • Wenjie Wang — 10 papers, h 8
  • Wenjie Wang — 10 papers, h 4
  • Wenjie Wang — 10 papers, h 3

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

collaborators

4 papers

cs.CR2026

How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions

Yukai Zhou, Feiyang Lu, Xiaokai Mao +2

Jailbreak attacks on large language models are usually evaluated by attacker-centric metrics such as attack success rate (ASR), yet an attack that breaks a model is not necessarily…

cs.CL2024

LinkPrompt: Natural and Universal Adversarial Attacks on Prompt-based Language Models

Yue Xu, Wenjie Wang

Prompt-based learning is a new language model training paradigm that adapts the Pre-trained Language Models (PLMs) to downstream tasks, which revitalizes the performance benchmarks…

cs.LG2024

Certified PEFTSmoothing: Parameter-Efficient Fine-Tuning with Randomized Smoothing

Chengyan Fu, Wenjie Wang

Randomized smoothing is the primary certified robustness method for accessing the robustness of deep learning models to adversarial perturbations in the l2-norm, by adding isotropi…

cs.CL2024

Don't Say No: Jailbreaking LLM by Suppressing Refusal

Yukai Zhou, Jian Lou, Zhijie Huang +3

Ensuring the safety alignment of Large Language Models (LLMs) is critical for generating responses consistent with human values. However, LLMs remain vulnerable to jailbreaking att…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.