5 citations · 12 across the 11 of their papers we have counts for
11 papers
Image-based Prompt Injection: Hijacking Multimodal LLMs through Visually Embedded Adversarial Instructions
Neha Nagaraja, Lan Zhang, Zhilong Wang +2
Multimodal Large Language Models (MLLMs) integrate vision and text to power applications, but this integration introduces new vulnerabilities. We study Image-based Prompt Injection…
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…
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…
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…
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…
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…
Which Features are Learned by CodeBert: An Empirical Study of the BERT-based Source Code Representation Learning
Lan Zhang, Chen Cao, Zhilong Wang +1
The Bidirectional Encoder Representations from Transformers (BERT) were proposed in the natural language process (NLP) and shows promising results. Recently researchers applied the…
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…
Spotting Silent Buffer Overflows in Execution Trace through Graph Neural Network Assisted Data Flow Analysis
Zhilong Wang, Li Yu, Suhang Wang +1
A software vulnerability could be exploited without any visible symptoms. When no source code is available, although such silent program executions could cause very serious damage,…
Using Deep Learning to Solve Computer Security Challenges: A Survey
Yoon-Ho Choi, Peng Liu, Zitong Shang +5
Although using machine learning techniques to solve computer security challenges is not a new idea, the rapidly emerging Deep Learning technology has recently triggered a substanti…
GPT Conjecture: Understanding the Trade-offs between Granularity, Performance and Timeliness in Control-Flow Integrity
Zhilong Wang, Peng Liu
Performance/security trade-off is widely noticed in CFI research, however, we observe that not every CFI scheme is subject to the trade-off. Motivated by the key observation, we as…