4 citations · 5 across the 14 of their papers we have counts for
17 papers
Defending Against Dormant Poisoning Attacks Across Language and Multimodal Agents
Wonjun Lee, Vaidehi Patil, Zaid Khan +4
Recent work shows that attackers can implant dormant malicious behaviors that remain hidden at release but emerge after benign fine-tuning. As foundation models are used as agents,…
Scaled Companion Linearizations for Coefficientwise Backward Stability
Javier Pérez
A central goal in solving a polynomial eigenvalue problem is to compute eigenpairs that are exact for a nearby polynomial, with each coefficient perturbation bounded by a modest mu…
Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge
Wonjun Lee, Kyungsik Yang, Gaeun Ji +5
LLMs have advanced rapidly, raising growing concerns about their safety. Recent work has proposed approaches to detect and defend against attacks including defenses at decoding sta…
EvoHarnessBench: Can Your Agents Keep Pace with an Evolving Harness?
Zixuan Ke, Vaidehi Patil, Haizhou Shi +9
Modern LLM-based agents operate through a harness of tools, reusable skills, and specialist agents that shapes what they observe and what they can do. In practice, this harness con…
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu +1
With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or unsafe cross-modal associatio…
Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind
Hanqi Xiao, Vaidehi Patil, Zaid Khan +3
As large language models (LLMs) become the engine behind conversational systems, their ability to reason about the intentions and states of their dialogue partners (i.e., form and…
Hierarchy-Aware Multimodal Unlearning for Medical AI
Fengli Wu, Vaidehi Patil, Jaehong Yoon +2
Pretrained Multimodal Large Language Models (MLLMs) are increasingly used in sensitive domains such as medical AI, where privacy regulations like HIPAA and GDPR require specific re…
Generalized Correctness Models: Learning Calibrated and Model-Agnostic Correctness Predictors from Historical Patterns
Hanqi Xiao, Vaidehi Patil, Hyunji Lee +2
Generating accurate and calibrated confidence estimates is critical for deploying LLMs in high-stakes or user-facing applications, and remains an open challenge. Prior research has…
The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration
Vaidehi Patil, Elias Stengel-Eskin, Mohit Bansal
As large language models (LLMs) become integral to multi-agent systems, new privacy risks emerge that extend beyond memorization, direct inference, or single-turn evaluations. In p…
Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation
Vaidehi Patil, Yi-Lin Sung, Peter Hase +3
LLMs trained on massive datasets may inadvertently acquire sensitive information such as personal details and potentially harmful content. This risk is further heightened in multim…
UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning
Vaidehi Patil, Elias Stengel-Eskin, Mohit Bansal
User specifications or legal frameworks often require information to be removed from pretrained models, including large language models (LLMs). This requires deleting or "forgettin…
SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation
Jaehong Yoon, Shoubin Yu, Vaidehi Patil +2
Recent advances in diffusion models have significantly enhanced their ability to generate high-quality images and videos, but they have also increased the risk of producing unsafe…
Debiasing Multimodal Models via Causal Information Minimization
Vaidehi Patil, Adyasha Maharana, Mohit Bansal
Most existing debiasing methods for multimodal models, including causal intervention and inference methods, utilize approximate heuristics to represent the biases, such as shallow…
Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks
Vaidehi Patil, Peter Hase, Mohit Bansal
Pretrained language models sometimes possess knowledge that we do not wish them to, including memorized personal information and knowledge that could be used to harm people. They c…
GEMS: Scene Expansion using Generative Models of Graphs
Rishi Agarwal, Tirupati Saketh Chandra, Vaidehi Patil +3
Applications based on image retrieval require editing and associating in intermediate spaces that are representative of the high-level concepts like objects and their relationships…
Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages
Vaidehi Patil, Partha Talukdar, Sunita Sarawagi
Pre-trained multilingual language models such as mBERT and XLM-R have demonstrated great potential for zero-shot cross-lingual transfer to low web-resource languages (LRL). However…
Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study
Yash Khemchandani, Sarvesh Mehtani, Vaidehi Patil +3
Recent research in multilingual language models (LM) has demonstrated their ability to effectively handle multiple languages in a single model. This holds promise for low web-resou…