Maya Pavlova — accepted AI-conference papers

2025

AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents

Arman Zharmagambetov, Chuan Guo, Ivan Evtimov, Maya Pavlova, Ruslan Salakhutdinov, Kamalika Chaudhuri

NeurIPS 2025poster

Autonomous AI agents that can follow instructions and perform complex multi-step tasks have tremendous potential to boost human productivity. However, to perform many of these tasks, the agents need access to personal information from their users, raising the question of whether they are capable of…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Automated Red Teaming with GOAT: the Generative Offensive Agent Tester

Maya Pavlova, Erik Brinkman, Krithika Iyer, Vítor Albiero, Joanna Bitton, Hailey Nguyen +3

ICML 2025poster

Red teaming aims to assess how large language models (LLMs) can produce content that violates norms, policies, and rules set forth during their safety training. However, most existing automated methods in literature are not representative of the way common users exploit the multi-turn conversational…

Cited by 8 Source ↗PDF ↗Scholar ↗

2022

Adversarial Text Normalization

Joanna Bitton, Maya Pavlova, Ivan Evtimov

NAACL 2022industry

Text-based adversarial attacks are becoming more commonplace and accessible to general internet users. As these attacks proliferate, the need to address the gap in model robustness becomes imminent. While retraining on adversarial data may increase performance, there remains an additional class of c…

Cited by 3 Source ↗PDF ↗Scholar ↗