62 citations · 92 across the 22 of their papers we have counts for
23 papers
Beyond Episodic Evaluation: Memory Architectural Bottlenecks in Sequential Embodied Question Answering
Zikui Cai, Kaushal Janga, Tan Dat Dao +15
Embodied question answering (EQA) is traditionally evaluated under an episodic formulation, where agents solve each task independently and reset internal state between episodes. Ho…
DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents
Zhaorun Chen, Xun Liu, Haibo Tong +14
AI agents are increasingly deployed across diverse domains to automate complex workflows through long-horizon and high-stakes action executions. Due to their high capability and fl…
AudioGuard: Toward Comprehensive Audio Safety Protection Across Diverse Threat Models
Mintong Kang, Chen Fang, Bo Li
Audio has rapidly become a primary interface for foundation models, powering real-time voice assistants. Ensuring safety in audio systems is inherently more complex than just "unsa…
FG-OrIU: Towards Better Forgetting via Feature-Gradient Orthogonality for Incremental Unlearning
Qian Feng, JiaHang Tu, Mintong Kang +3
Incremental unlearning (IU) is critical for pre-trained models to comply with sequential data deletion requests, yet existing methods primarily suppress parameters or confuse knowl…
Mitigating Indirect Prompt Injection via Instruction-Following Intent Analysis
Mintong Kang, Chong Xiang, Sanjay Kariyappa +3
Indirect prompt injection attacks (IPIAs), where large language models (LLMs) follow malicious instructions hidden in input data, pose a critical threat to LLM-powered agents. In t…
SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning
Kaiwen Zhou, Ahmed Elgohary, A S M Iftekhar +1
The ability of LLM agents to plan and invoke tools exposes them to new safety risks, making a comprehensive red-teaming system crucial for discovering vulnerabilities and ensuring…
ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks
Zhaorun Chen, Xun Liu, Mintong Kang +4
As vision-language models (VLMs) gain prominence, their multimodal interfaces also introduce new safety vulnerabilities, making the safety evaluation challenging and critical. Exis…
Poly-Guard: Massive Multi-Domain Safety Policy-Grounded Guardrail Dataset
Mintong Kang, Zhaorun Chen, Chejian Xu +6
As LLMs become widespread across diverse applications, concerns about the security and safety of LLM interactions have intensified. Numerous guardrail models and benchmarks have be…
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
Chejian Xu, Jiawei Zhang, Zhaorun Chen +22
Multimodal foundation models (MMFMs) play a crucial role in various applications, including autonomous driving, healthcare, and virtual assistants. However, several studies have re…
ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
Zhaorun Chen, Mintong Kang, Bo Li
Autonomous agents powered by foundation models have seen widespread adoption across various real-world applications. However, they remain highly vulnerable to malicious instruction…
FairGen: Controlling Sensitive Attributes for Fair Generations in Diffusion Models via Adaptive Latent Guidance
Mintong Kang, Vinayshekhar Bannihatti Kumar, Shamik Roy +4
Text-to-image diffusion models often exhibit biases toward specific demographic groups, such as generating more males than females when prompted to generate images of engineers, ra…
AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models
Mintong Kang, Chejian Xu, Bo Li
Recent advancements in large audio-language models (LALMs) have enabled speech-based user interactions, significantly enhancing user experience and accelerating the deployment of L…
AdvAgent: Controllable Blackbox Red-teaming on Web Agents
Chejian Xu, Mintong Kang, Jiawei Zhang +5
Foundation model-based agents are increasingly used to automate complex tasks, enhancing efficiency and productivity. However, their access to sensitive resources and autonomous de…
EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage
Zeyi Liao, Lingbo Mo, Chejian Xu +6
Generalist web agents have demonstrated remarkable potential in autonomously completing a wide range of tasks on real websites, significantly boosting human productivity. However,…
-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning
Mintong Kang, Bo Li
As LLMs become increasingly prevalent across various applications, it is critical to establish safety guardrails to moderate input/output content of LLMs. Existing guardrail models…
Certifiably Byzantine-Robust Federated Conformal Prediction
Mintong Kang, Zhen Lin, Jimeng Sun +2
Conformal prediction has shown impressive capacity in constructing statistically rigorous prediction sets for machine learning models with exchangeable data samples. The siloed dat…
COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits
Mintong Kang, Nezihe Merve Gürel, Linyi Li +1
Conformal prediction has shown spurring performance in constructing statistically rigorous prediction sets for arbitrary black-box machine learning models, assuming the data is exc…
C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models
Mintong Kang, Nezihe Merve Gürel, Ning Yu +2
Despite the impressive capabilities of large language models (LLMs) across diverse applications, they still suffer from trustworthiness issues, such as hallucinations and misalignm…
DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification
Mintong Kang, Dawn Song, Bo Li
Diffusion-based purification defenses leverage diffusion models to remove crafted perturbations of adversarial examples and achieve state-of-the-art robustness. Recent studies show…
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Boxin Wang, Weixin Chen, Hengzhi Pei +16
Generative Pre-trained Transformer (GPT) models have exhibited exciting progress in their capabilities, capturing the interest of practitioners and the public alike. Yet, while the…
Fairness in Federated Learning via Core-Stability
Bhaskar Ray Chaudhury, Linyi Li, Mintong Kang +2
Federated learning provides an effective paradigm to jointly optimize a model benefited from rich distributed data while protecting data privacy. Nonetheless, the heterogeneity nat…
Certifying Some Distributional Fairness with Subpopulation Decomposition
Mintong Kang, Linyi Li, Maurice Weber +3
Extensive efforts have been made to understand and improve the fairness of machine learning models based on observational metrics, especially in high-stakes domains such as medical…
Label-Assemble: Leveraging Multiple Datasets with Partial Labels
Mintong Kang, Bowen Li, Zengle Zhu +4
The success of deep learning relies heavily on large labeled datasets, but we often only have access to several small datasets associated with partial labels. To address this probl…