Sheng Zhong
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Crypto×2Software Eng.×1AI×1
Frequent co-authors
Research Timeline
2026
Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors
This paper introduces a novel supply-chain attack that uses model code backdoors to actively steal sensitive secrets from local LLM fine-tuning datasets, bypassing current privacy defenses.
Usability as a Weapon: Attacking the Safety of LLM-Based Code Generation via Usability Requirements
This paper introduces UPAttack, a novel threat model demonstrating that focusing on explicit usability requirements can cause LLMs to generate insecure code by neglecting implicit security constraints, and proposes U-SPLOIT to automate this attack.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.SERecentMay 11, 2026
Usability as a Weapon: Attacking the Safety of LLM-Based Code Generation via Usability Requirements
This paper introduces UPAttack, a novel threat model demonstrating that focusing on explicit usability requirements can cause LLMs to generate insecure code by neglecting implicit security constraints…
View →
cs.CRcs.AIRecentApr 30, 2026