163 citations · 256 across the 13 of their papers we have counts for
14 papers
Search-GRT: Guided Retrieval Training of Search Agents to Optimize for Complex Question Answering
Aounon Kumar, Sudipta Paul, Vivek Kulkarni +2
The effective use of search engines by large language models (LLMs) remains a significant challenge, particularly in complex, multi-hop question-answering (MHQA) tasks. These tasks…
Manipulating Large Language Models to Increase Product Visibility
Aounon Kumar, Himabindu Lakkaraju
Large language models (LLMs) are increasingly being integrated into search engines to provide natural language responses tailored to user queries. Customers and end-users are also…
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
Mehrdad Saberi, Vinu Sankar Sadasivan, Keivan Rezaei +4
In light of recent advancements in generative AI models, it has become essential to distinguish genuine content from AI-generated one to prevent the malicious usage of fake materia…
Certifying LLM Safety against Adversarial Prompting
Aounon Kumar, Chirag Agarwal, Suraj Srinivas +3
Large language models (LLMs) are vulnerable to adversarial attacks that add malicious tokens to an input prompt to bypass the safety guardrails of an LLM and cause it to produce ha…
Provable Robustness for Streaming Models with a Sliding Window
Aounon Kumar, Vinu Sankar Sadasivan, Soheil Feizi
The literature on provable robustness in machine learning has primarily focused on static prediction problems, such as image classification, in which input samples are assumed to b…
Can AI-Generated Text be Reliably Detected?
Vinu Sankar Sadasivan, Aounon Kumar, Sriram Balasubramanian +2
Large Language Models (LLMs) perform impressively well in various applications. However, the potential for misuse of these models in activities such as plagiarism, generating fake…
Certifying Model Accuracy under Distribution Shifts
Aounon Kumar, Alexander Levine, Tom Goldstein +1
Certified robustness in machine learning has primarily focused on adversarial perturbations of the input with a fixed attack budget for each point in the data distribution. In this…
Policy Smoothing for Provably Robust Reinforcement Learning
Aounon Kumar, Alexander Levine, Soheil Feizi
The study of provable adversarial robustness for deep neural networks (DNNs) has mainly focused on static supervised learning tasks such as image classification. However, DNNs have…
Center Smoothing: Certified Robustness for Networks with Structured Outputs
Aounon Kumar, Tom Goldstein
The study of provable adversarial robustness has mostly been limited to classification tasks and models with one-dimensional real-valued outputs. We extend the scope of certifiable…
Certifying Confidence via Randomized Smoothing
Aounon Kumar, Alexander Levine, Soheil Feizi +1
Randomized smoothing has been shown to provide good certified-robustness guarantees for high-dimensional classification problems. It uses the probabilities of predicting the top tw…
Tight Second-Order Certificates for Randomized Smoothing
Alexander Levine, Aounon Kumar, Thomas Goldstein +1
Randomized smoothing is a popular way of providing robustness guarantees against adversarial attacks: randomly-smoothed functions have a universal Lipschitz-like bound, allowing fo…
Detection as Regression: Certified Object Detection by Median Smoothing
Ping-yeh Chiang, Michael J. Curry, Ahmed Abdelkader +3
Despite the vulnerability of object detectors to adversarial attacks, very few defenses are known to date. While adversarial training can improve the empirical robustness of image…
Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness
Aounon Kumar, Alexander Levine, Tom Goldstein +1
Randomized smoothing, using just a simple isotropic Gaussian distribution, has been shown to produce good robustness guarantees against -norm bounded adversaries. In this w…
On the cost of essentially fair clusterings
Ioana O. Bercea, Martin Groß, Samir Khuller +4
Clustering is a fundamental tool in data mining. It partitions points into groups (clusters) and may be used to make decisions for each point based on its group. However, this proc…