Author name cluster

Ivan Evtimov

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

AdvPrefix: An Objective for Nuanced LLM Jailbreaks

Sicheng Zhu
Brandon Amos
Yuandong Tian
Chuan Guo
Ivan Evtimov

Many jailbreak attacks on large language models (LLMs) rely on a common objective: making the model respond with the prefix ``Sure, here is (harmful request)''. While straightforward, this objective has two limitations: limited control over model behaviors, yielding incomplete or unrealistic jailbroken responses, and a rigid format that hinders optimization. We introduce AdvPrefix, a plug-and-play prefix-forcing objective that selects one or more model-dependent prefixes by combining two criteria: high prefilling attack success rates and low negative log-likelihood. AdvPrefix integrates seamlessly into existing jailbreak attacks to mitigate the previous limitations for free. For example, replacing GCG's default prefixes on Llama-3 improves nuanced attack success rates from 14\% to 80\%, revealing that current safety alignment fails to generalize to new prefixes. Code and selected prefixes are released.

PDF Details

NeurIPS Conference 2025 Conference Paper

AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents

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

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 using it appropriately. In this work, we introduce a new benchmark AgentDAM that measures if AI web-navigation agents follow the privacy principle of "data minimization". For the purposes of our benchmark, data minimization means that the agent uses a piece of potentially sensitive information only if it is "necessary" to complete a particular task. Our benchmark simulates realistic web interaction scenarios end-to-end and is adaptable to all existing web navigation agents. We use AgentDAM to evaluate how well AI agents built on top of GPT-4, Llama-3 and Claude can limit processing of potentially private information, and show that they are prone to inadvertent use of unnecessary sensitive information. We also propose a prompting-based defense that reduces information leakage, and demonstrate that our end-to-end benchmarking provides a more realistic measure than probing LLMs about privacy. Our results highlight that further research is needed to develop AI agents that can prioritize data minimization at inference time. We open source our benchmark at: https: //github. com/facebookresearch/ai-agent-privacy

PDF Details

ICML Conference 2025 Conference Paper

Automated Red Teaming with GOAT: the Generative Offensive Agent Tester

Maya Pavlova
Erik Brinkman
Krithika Iyer
Vítor Albiero
Joanna Bitton
Hailey Nguyen
Cristian Canton Ferrer
Ivan Evtimov

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 nature of AI models. While manual testing addresses this gap, it is an inefficient and often expensive process. To address these limitations, we introduce the Generative Offensive Agent Tester (GOAT), an automated agentic red teaming system that simulates plain language adversarial conversations while leveraging multiple adversarial prompting techniques to identify vuLnerabilities in LLMs. We instantiate GOAT with 7 red teaming attacks by prompting a general purpose model in a way that encourages reasoning through the choices of methods available, the current target model’s response, and the next steps. Our approach is designed to be extensible and efficient, allowing human testers to focus on exploring new areas of risk while automation covers the scaled adversarial stress-testing of known risk territory. We present the design and evaluation of GOAT, demonstrating its effectiveness in identifying vulnerabilities in state-of-the-art LLMs, with an ASR@10 of 96% against smaller models such as Llama 3. 1 8B, and 91% against Llama 3. 1 70B and 94% for GPT-4o when evaluated against larger models on the JailbreakBench dataset.

Details

ICLR Conference 2025 Conference Paper

Persistent Pre-training Poisoning of LLMs

Yiming Zhang
Javier Rando
Ivan Evtimov
Jianfeng Chi
Eric Michael Smith
Nicholas Carlini
Florian Tramèr
Daphne Ippolito

Large language models are pre-trained on uncurated text datasets consisting of trillions of tokens scraped from the Web. Prior work has shown that: (1) web-scraped pre-training datasets can be practically poisoned by malicious actors; and (2) adversaries can compromise language models after poisoning fine-tuning datasets. Our work evaluates for the first time whether language models can also be \emph{compromised during pre-training}, with a focus on the persistence of pre-training attacks after models are fine-tuned as helpful and harmless chatbots (i.e., after SFT and DPO). We pre-train a series of LLMs from scratch to measure the impact of a potential poisoning adversary under four different attack objectives (denial-of-service, belief manipulation, jailbreaking, and prompt stealing), and across a wide range of model sizes (from 600M to 7B). Our main result is that poisoning only 0.1% of a model's pre-training dataset is sufficient for three out of four attacks to measurably persist through post-training. Moreover, simple attacks like denial-of-service persist through post-training with a poisoning rate of only 0.001%.

Details

NeurIPS Conference 2025 Conference Paper

WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks

Ivan Evtimov
Arman Zharmagambetov
Aaron Grattafiori
Chuan Guo
Kamalika Chaudhuri

Autonomous UI agents powered by AI have tremendous potential to boost human productivity by automating routine tasks such as filing taxes and paying bills. However, a major challenge in unlocking their full potential is security, which is exacerbated by the agent's ability to take action on their user's behalf. Existing tests for prompt injections in web agents either over-simplify the threat by testing unrealistic scenarios or giving the attacker too much power, or look at single-step isolated tasks. To more accurately measure progress for secure web agents, we introduce WASP – a new publicly available benchmark for end-to-end evaluation of Web Agent Security against Prompt Injection attacks. Evaluating with WASP shows that even top-tier AI models, including those with advanced reasoning capabilities, can be deceived by simple, low-effort human-written injections in very realistic scenarios. Our end-to-end evaluation reveals a previously unobserved insight: while attacks partially succeed in up to 86% of the case, even state-of-the-art agents often struggle to fully complete the attacker goals – highlighting the current state of security by incompetence. Code and data are available at https: //github. com/facebookresearch/wasp.

PDF Details

ICLR Conference 2023 Conference Paper

ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations

Badr Youbi Idrissi
Diane Bouchacourt
Randall Balestriero
Ivan Evtimov
Caner Hazirbas
Nicolas Ballas
Pascal Vincent
Michal Drozdzal

Deep learning vision systems are widely deployed across applications where reliability is critical. However, even today's best models can fail to recognize an object when its pose, lighting, or background varies. While existing benchmarks surface examples challenging for models, they do not explain why such mistakes arise. To address this need, we introduce ImageNet-X—a set of sixteen human annotations of factors such as pose, background, or lighting the entire ImageNet-1k validation set as well as a random subset of 12k training images. Equipped with ImageNet-X, we investigate 2,200 current recognition models and study the types of mistakes as a function of model’s (1) architecture, e.g. transformer vs. convolutional, (2) learning paradigm, e.g. supervised vs. self-supervised, and (3) training procedures, e.g., data augmentation. Regardless of these choices, we find models have consistent failure modes across ImageNet-X categories. We also find that while data augmentation can improve robustness to certain factors, they induce spill-over effects to other factors. For example, color-jitter augmentation improves robustness to color and brightness, but surprisingly hurts robustness to pose. Together, these insights suggest to advance the robustness of modern vision models, future research should focus on collecting additional data and understanding data augmentation schemes. Along with these insights, we release a toolkit based on ImageNet-X to spur further study into the mistakes image recognition systems make.

Details