10 citations · 24 across the 21 of their papers we have counts for
21 papers
Understanding Content Moderation in Large Language Models through Restricted Books: From Refusal to Warning
Xucheng Yu, Emily Knox, Haohan Wang
As large language models enter everyday information pipelines, understanding how they handle sensitive topics matters as much as understanding whether they handle them at all. We s…
Preference Tuning as Spectral Update Reorganization
Peiyan Zhang, Haibo Jin, Liying Kang +1
Preference-based post-training is usually understood through endpoint behavior, yet the learned update that produces this behavior remains largely opaque. We study RLHF and related…
Security--Fidelity Tradeoffs: The Hidden Cost of Prompt Injection Defense
Mitchell Hermon, Rahul Gupta, Weitong Ruan +2
We identify a security-fidelity tradeoff in defending LLMs against indirect prompt injection: defenses resist injected instructions largely by suppressing untrusted text, which cor…
SCI-Defense: Defending Manipulation Attacks from Generative Engine Optimization
Xucheng Yu, Haibo Jin, Huimin Zeng +1
LLM-based ranking systems are vulnerable to Generative Engine Optimization (GEO) attacks, where adversaries inject semantic signals into product descriptions to artificially boost…
TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization
Lucheng Fu, Ye Yu, Yiyang Wang +4
Large language models (LLMs) are highly sensitive to the prompts used to specify task objectives and behavioral constraints. Many recent prompt optimization methods iteratively rew…
Controlling Output Rankings in LLM-Based Search via Generative Engine Optimization
Haibo Jin, Ruoxi Chen, Peiyan Zhang +4
The way customers search for and choose products is changing with the rise of large language models (LLMs). LLM-based search, or generative engines, provides direct product recomme…
Agent Primitives: Reusable Latent Building Blocks for Multi-Agent Systems
Haibo Jin, Peng Kuang, Ye Yu +2
While existing multi-agent systems (MAS) can handle complex problems by enabling collaboration among multiple agents, they are often highly task-specific, relying on manually craft…
Crafting Adversarial Inputs for Large Vision-Language Models Using Black-Box Optimization
Jiwei Guan, Haibo Jin, Haohan Wang
Recent advancements in Large Vision-Language Models (LVLMs) have shown groundbreaking capabilities across diverse multimodal tasks. However, these models remain vulnerable to adver…
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs
Haibo Jin, Ruoxi Chen, Peiyan Zhang +3
As Large Language Models (LLMs) become increasingly integral to various domains, their potential to generate harmful responses has prompted significant societal and regulatory conc…
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing
Peiyan Zhang, Haibo Jin, Liying Kang +1
Jailbreak attacks reveal critical vulnerabilities in Large Language Models (LLMs) by causing them to generate harmful or unethical content. Evaluating these threats is particularly…
From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models
Haibo Jin, Peiyan Zhang, Peiran Wang +2
Large foundation models (LFMs) are susceptible to two distinct vulnerabilities: hallucinations and jailbreak attacks. While typically studied in isolation, we observe that defenses…
Reasoning Can Hurt the Inductive Abilities of Large Language Models
Haibo Jin, Peiyan Zhang, Man Luo +1
Large Language Models (LLMs) have shown remarkable progress across domains, yet their ability to perform inductive reasoning - inferring latent rules from sparse examples - remains…
REVOLVE: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization
Peiyan Zhang, Haibo Jin, Leyang Hu +5
Recent advancements in large language models (LLMs) have significantly enhanced the ability of LLM-based systems to perform complex tasks through natural language processing and to…
DistDD: Distributed Data Distillation Aggregation through Gradient Matching
Peiran Wang, Haohan Wang
In this paper, we introduce DistDD, a novel approach within the federated learning framework that reduces the need for repetitive communication by distilling data directly on clien…
JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models
Haibo Jin, Leyang Hu, Xinnuo Li +4
The rapid evolution of artificial intelligence (AI) through developments in Large Language Models (LLMs) and Vision-Language Models (VLMs) has brought significant advancements acro…
Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters
Haibo Jin, Andy Zhou, Joe D. Menke +1
Large Language Models (LLMs) are typically harmless but remain vulnerable to carefully crafted prompts known as ``jailbreaks'', which can bypass protective measures and induce harm…
GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Models
Haibo Jin, Ruoxi Chen, Peiyan Zhang +2
The discovery of "jailbreaks" to bypass safety filters of Large Language Models (LLMs) and harmful responses have encouraged the community to implement safety measures. One major s…
Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
Andy Zhou, Bo Li, Haohan Wang
Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted…
Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models
Andy Zhou, Jindong Wang, Yu-Xiong Wang +1
We propose a conceptually simple and lightweight framework for improving the robustness of vision models through the combination of knowledge distillation and data augmentation. We…
Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models
Andy Zhou, Kai Yan, Michal Shlapentokh-Rothman +2
While language models (LMs) have shown potential across a range of decision-making tasks, their reliance on simple acting processes limits their broad deployment as autonomous agen…
CatchBackdoor: Backdoor Detection via Critical Trojan Neural Path Fuzzing
Haibo Jin, Ruoxi Chen, Jinyin Chen +3
The success of deep neural networks (DNNs) in real-world applications has benefited from abundant pre-trained models. However, the backdoored pre-trained models can pose a signific…