Tianshuo Cong

8 papers at tracked venues · 8 at CORE A* · active 2024–2025

DBLP profile ↗ORCID search ↗

Venues

AAAI ×2 S&P ×2 ACL ×1 NDSS ×1 NeurIPS ×1 USENIX Security ×1

Frequent coauthors

Xinlei He

×6

Yichen Gong

×2

Delong Ran

×2

Anyu Wang

×2

Xiaoyun Wang

×2

Xinyi Huang

×2

Sibo Yi

×1

Qi Li

×1

Jiaxing Song

×1

Jingyi Zheng

×1

Tianyi Hu

×1

Chuanchao Zang

×1

Papers

Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models
ACL 2025 ·
Sibo Yi
, Tianshuo Cong,
Xinlei He
,
Qi Li
,
Jiaxing Song
CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers
AAAI 2025 ·
Jingyi Zheng
,
Tianyi Hu
, Tianshuo Cong,
Xinlei He
ErrorTrace: A Black-Box Traceability Mechanism Based on Model Family Error Space
NeurIPS 2025 ·
Chuanchao Zang
,
Xiangtao Meng
,
Wenyu Chen
, Tianshuo Cong,
Yaxing Zha
,
Dong Qi
,
Zheng Li
,
Shanqing Guo
FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts
AAAI 2025 ·
Yichen Gong
,
Delong Ran
,
Jinyuan Liu
,
Conglei Wang
, Tianshuo Cong,
Anyu Wang
,
Sisi Duan
,
Xiaoyun Wang
From Purity to Peril: Backdooring Merged Models From "Harmless" Benign Components
USENIX Security 2025 ·
Lijin Wang
,
Jingjing Wang
, Tianshuo Cong,
Xinlei He
,
Zhan Qin
,
Xinyi Huang
PEFTGuard: Detecting Backdoor Attacks Against Parameter-Efficient Fine-Tuning
S&P 2025 ·
Zhen Sun
, Tianshuo Cong,
Yule Liu
,
Chenhao Lin
,
Xinlei He
,
Rongmao Chen
,
Xingshuo Han
,
Xinyi Huang
Safety Misalignment Against Large Language Models
NDSS 2025 ·
Yichen Gong
,
Delong Ran
,
Xinlei He
, Tianshuo Cong,
Anyu Wang
,
Xiaoyun Wang
Test-Time Poisoning Attacks Against Test-Time Adaptation Models
S&P 2024 · Tianshuo Cong,
Xinlei He
,
Yun Shen
,
Yang Zhang