27 citations · 41 across the 32 of their papers we have counts for
12 papers · 1 filter
Jev-Guard: Fast Routing and Auditing Agent Actions over Editable Policy Trees
Wenbin Hu, Huihao Jing, Haochen Shi +9
Agent harnesses require a low-latency guardrail model together with customizable audit policies. However, deploying an auto-regressive guardrail model remains challenging: such mod…
Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries
Ki Sen Hung, Xi Yang, Chang Liu +7
A central goal of LLM alignment is to balance helpfulness with harmlessness, yet these objectives conflict when the same knowledge serves both legitimate and malicious purposes. Th…
WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents
Yulin Chen, Tri Cao, Haoran Li +7
Web agents powered by vision-language models (VLMs) enable autonomous interaction with web environments by perceiving and acting on both visual and textual webpage content to accom…
Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods
Yulin Chen, Haoran Li, Yuan Sui +2
With the development of technology, large language models (LLMs) have dominated the downstream natural language processing (NLP) tasks. However, because of the LLMs' instruction-fo…
GSPR: Aligning LLM Safeguards as Generalizable Safety Policy Reasoners
Haoran Li, Jingru Zeng, Yulin Chen +8
As large language models (LLMs) are integrated into numerous applications, LLMs' safety becomes critical for both application developers and intended users. Currently, great effort…
TopicAttack: An Indirect Prompt Injection Attack via Topic Transition
Yulin Chen, Haoran Li, Yuexin Li +3
Large language models (LLMs) have shown remarkable performance across a range of NLP tasks. However, their strong instruction-following capabilities and inability to distinguish in…
Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction
Yulin Chen, Haoran Li, Yuan Sui +8
Large language models (LLMs) have demonstrated impressive performance and have come to dominate the field of natural language processing (NLP) across various tasks. However, due to…
Can Indirect Prompt Injection Attacks Be Detected and Removed?
Yulin Chen, Haoran Li, Yuan Sui +4
Prompt injection attacks manipulate large language models (LLMs) by misleading them to deviate from the original input instructions and execute maliciously injected instructions, b…
Defense Against Prompt Injection Attack by Leveraging Attack Techniques
Yulin Chen, Haoran Li, Zihao Zheng +3
With the advancement of technology, large language models (LLMs) have achieved remarkable performance across various natural language processing (NLP) tasks, powering LLM-integrate…
BaThe: Defense against the Jailbreak Attack in Multimodal Large Language Models by Treating Harmful Instruction as Backdoor Trigger
Yulin Chen, Haoran Li, Yirui Zhang +3
Multimodal Large Language Models (MLLMs) have showcased impressive performance in a variety of multimodal tasks. On the other hand, the integration of additional image modality may…
Federated Domain-Specific Knowledge Transfer on Large Language Models Using Synthetic Data
Haoran Li, Xinyuan Zhao, Dadi Guo +6
As large language models (LLMs) demonstrate unparalleled performance and generalization ability, LLMs are widely used and integrated into various applications. When it comes to sen…
Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models
Haoran Li, Yulin Chen, Zihao Zheng +4
With rapid advances, generative large language models (LLMs) dominate various Natural Language Processing (NLP) tasks from understanding to reasoning. Yet, language models' inheren…