VP
Vaidehi Patil
cs.CLcs.AIcs.CVcs.CRcs.LGcs.MAstat.ME
On Valency
published · living versionsW_tyvjz7z3·v1 · currentpublished
Defending Against Dormant Poisoning Attacks Across Language and Multimodal Agents
with Wonjun Lee, Zaid Khan, Yue Zhang, Hyunji Lee +2
1 version
Preprints & journals
12 papers in the corpus · 2021–2026Defending Against Dormant Poisoning Attacks Across Language and Multimodal Agents2610.24379v1 · Wonjun Lee, Vaidehi Patil, Zaid Khan et al.2026 · 0 citationsarXivon Valency
Why Do Agent Teams Fail Across Boundaries? A Failure Taxonomy for Agent-to-Agent Systems with Private States2610.19342v2 · Sarath Shekkizhar, Prathyusha Jwalapuram, Zixuan Ke et al.2026 · 0 citationsarXiv
Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge2610.07532v1 · Wonjun Lee, Kyungsik Yang, Gaeun Ji et al.2026 · 0 citationsarXiv
Generalized Correctness Models: Learning Calibrated and Model-Agnostic Correctness Predictors from Historical Patterns2509.24988v2 · Hanqi Xiao, Vaidehi Patil, Hyunji Lee et al.2025 · 0 citationsarXiv
The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration2509.14284v1 · Vaidehi Patil, Elias Stengel-Eskin, Mohit Bansal2025 · 0 citationsarXiv
Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation2505.01456v1 · Vaidehi Patil, Yi-Lin Sung, Peter Hase et al.2025 · 0 citationsarXiv
SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation2410.12761v2 · Jaehong Yoon, Shoubin Yu, Vaidehi Patil et al.2024 · 2 citationsarXiv
Debiasing Multimodal Models via Causal Information Minimization2311.16941v1 · Vaidehi Patil, Adyasha Maharana, Mohit Bansal2023 · 0 citationsarXiv
Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks2309.17410v1 · Vaidehi Patil, Peter Hase, Mohit Bansal2023 · 6 citationsarXiv
GEMS: Scene Expansion using Generative Models of Graphs2207.03729v1 · Rishi Agarwal, Tirupati Saketh Chandra, Vaidehi Patil et al.2022 · 2 citationsarXiv
Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages2203.01976v2 · Vaidehi Patil, Partha Talukdar, Sunita Sarawagi2022 · 17 citationsarXiv
Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study2106.03958v2 · Yash Khemchandani, Sarvesh Mehtani, Vaidehi Patil et al.2021 · 23 citationsarXiv
Career total: 20 works. 12 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.