activity
20192026
most citedHow Does Naming Affect LLMs on Code Analysis Tasks?

5 citations · 7 across the 8 of their papers we have counts for

collaborators
Showing cs.CRShow all

9 papers · 1 filter

cs.CR2025

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt

Zhilong Wang, Neha Nagaraja, Lan Zhang +3

LLM agents are widely used as agents for customer support, content generation, and code assistance. However, they are vulnerable to prompt injection attacks, where adversarial inpu…

cs.CR2024

Hide Your Malicious Goal Into Benign Narratives: Jailbreak Large Language Models through Carrier Articles

Zhilong Wang, Haizhou Wang, Nanqing Luo +4

Large Language Model (LLM) jailbreak refers to a type of attack aimed to bypass the safeguard of an LLM to generate contents that are inconsistent with the safe usage guidelines. B…

cs.CR2024

Hidden You Malicious Goal Into Benign Narratives: Jailbreak Large Language Models through Logic Chain Injection

Zhilong Wang, Yebo Cao, Peng Liu

Jailbreak attacks on Language Model Models (LLMs) entail crafting prompts aimed at exploiting the models to generate malicious content. Existing jailbreak attacks can successfully…

cs.CR2024

A hybrid LLM workflow can help identify user privilege related variables in programs of any size

Haizhou Wang, Zhilong Wang, Peng Liu

Many programs involves operations and logic manipulating user privileges, which is essential for the security of an organization. Therefore, one common malicious goal of attackers…

cs.CR2023★ 5 cited

How Does Naming Affect LLMs on Code Analysis Tasks?

Zhilong Wang, Lan Zhang, Chen Cao +3

The Large Language Models (LLMs), such as GPT and BERT, were proposed for natural language processing (NLP) and have shown promising results as general-purpose language models. An…

cs.CR2021

Identifying Non-Control Security-Critical Data through Program Dependence Learning

Zhilong Wang, Haizhou Wang, Hong Hu +1

As control-flow protection gets widely deployed, it is difficult for attackers to corrupt control-data and achieve control-flow hijacking. Instead, data-oriented attacks, which man…