491 citations · 1.1k across the 14 of their papers we have counts for
15 papers
How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
Mateusz Dziemian, Maxwell Lin, Xiaohan Fu +28
LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure…
Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations
Christian Tomani, Kamalika Chaudhuri, Ivan Evtimov +2
A major barrier towards the practical deployment of large language models (LLMs) is their lack of reliability. Three situations where this is particularly apparent are correctness,…
VPA: Fully Test-Time Visual Prompt Adaptation
Jiachen Sun, Mark Ibrahim, Melissa Hall +4
Textual prompt tuning has demonstrated significant performance improvements in adapting natural language processing models to a variety of downstream tasks by treating hand-enginee…
Code Llama: Open Foundation Models for Code
Baptiste Rozière, Jonas Gehring, Fabian Gloeckle +23
We release Code Llama, a family of large language models for code based on Llama 2 providing state-of-the-art performance among open models, infilling capabilities, support for lar…
You Only Need a Good Embeddings Extractor to Fix Spurious Correlations
Raghav Mehta, Vítor Albiero, Li Chen +4
Spurious correlations in training data often lead to robustness issues since models learn to use them as shortcuts. For example, when predicting whether an object is a cow, a model…
A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others
Zhiheng Li, Ivan Evtimov, Albert Gordo +5
Machine learning models have been found to learn shortcuts -- unintended decision rules that are unable to generalize -- undermining models' reliability. Previous works address thi…
ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations
Badr Youbi Idrissi, Diane Bouchacourt, Randall Balestriero +7
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,…
Adversarial Text Normalization
Joanna Bitton, Maya Pavlova, Ivan Evtimov
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…
Disrupting Model Training with Adversarial Shortcuts
Ivan Evtimov, Ian Covert, Aditya Kusupati +1
When data is publicly released for human consumption, it is unclear how to prevent its unauthorized usage for machine learning purposes. Successful model training may be preventabl…
FoggySight: A Scheme for Facial Lookup Privacy
Ivan Evtimov, Pascal Sturmfels, Tadayoshi Kohno
Advances in deep learning algorithms have enabled better-than-human performance on face recognition tasks. In parallel, private companies have been scraping social media and other…
Adversarial Evaluation of Multimodal Models under Realistic Gray Box Assumption
Ivan Evtimov, Russel Howes, Brian Dolhansky +2
This work examines the vulnerability of multimodal (image + text) models to adversarial threats similar to those discussed in previous literature on unimodal (image- or text-only)…
Security and Machine Learning in the Real World
Ivan Evtimov, Weidong Cui, Ece Kamar +3
Machine learning (ML) models deployed in many safety- and business-critical systems are vulnerable to exploitation through adversarial examples. A large body of academic research h…
Physical Adversarial Examples for Object Detectors
Kevin Eykholt, Ivan Evtimov, Earlence Fernandes +6
Deep neural networks (DNNs) are vulnerable to adversarial examples-maliciously crafted inputs that cause DNNs to make incorrect predictions. Recent work has shown that these attack…
Note on Attacking Object Detectors with Adversarial Stickers
Kevin Eykholt, Ivan Evtimov, Earlence Fernandes +6
Deep learning has proven to be a powerful tool for computer vision and has seen widespread adoption for numerous tasks. However, deep learning algorithms are known to be vulnerable…
Robust Physical-World Attacks on Deep Learning Models
Kevin Eykholt, Ivan Evtimov, Earlence Fernandes +6
Recent studies show that the state-of-the-art deep neural networks (DNNs) are vulnerable to adversarial examples, resulting from small-magnitude perturbations added to the input. G…