382 citations · 853 across the 32 of their papers we have counts for
35 papers
ChronoSSM: Training for Temporally Aware Representations in Autoregressive State Space Models
Adrien Schoen, Nachiketa Ratnakar Patil, Arjun Bhagoji +1
Modern sequence models, from Transformers to State Space Models, have enabled powerful generative modeling across diverse domains, yet they are typically trained to predict what ha…
Jailbreaking for the Average Jane: Choosing Optimal Jailbreaks via Bandit Algorithms for Automatically Enhanced Queries
Prarabdh Shukla, Ritik, Suhas Rao +2
With a profusion of jailbreaks for LLMs now widely known, a growing concern is that non-expert malicious actors ("the average Jane") could elicit actionable responses to malicious…
Silencing Empowerment, Allowing Bigotry: Auditing the Moderation of Hate Speech on Twitch
Prarabdh Shukla, Wei Yin Chong, Yash Patel +3
To meet the demands of content moderation, online platforms have resorted to automated systems. Newer forms of real-time engagement(, users commenting on live stream…
NetSSM: Multi-Flow and State-Aware Network Trace Generation using State Space Models
Andrew Chu, Xi Jiang, Shinan Liu +4
Access to raw network traffic data is essential for many computer networking tasks, from traffic modeling to performance evaluation. Unfortunately, this data is scarce due to high…
Adapting to Evolving Adversaries with Regularized Continual Robust Training
Sihui Dai, Christian Cianfarani, Arjun Bhagoji +2
Robust training methods typically defend against specific attack types, such as Lp attacks with fixed budgets, and rarely account for the fact that defenders may encounter new atta…
MYCROFT: Towards Effective and Efficient External Data Augmentation
Zain Sarwar, Van Tran, Arjun Nitin Bhagoji +3
Machine learning (ML) models often require large amounts of data to perform well. When the available data is limited, model trainers may need to acquire more data from external sou…
Feasibility of State Space Models for Network Traffic Generation
Andrew Chu, Xi Jiang, Shinan Liu +4
Many problems in computer networking rely on parsing collections of network traces (e.g., traffic prioritization, intrusion detection). Unfortunately, the availability and utility…
"Community Guidelines Make this the Best Party on the Internet": An In-Depth Study of Online Platforms' Content Moderation Policies
Brennan Schaffner, Arjun Nitin Bhagoji, Siyuan Cheng +7
Moderating user-generated content on online platforms is crucial for balancing user safety and freedom of speech. Particularly in the United States, platforms are not subject to le…
Towards Scalable and Robust Model Versioning
Wenxin Ding, Arjun Nitin Bhagoji, Ben Y. Zhao +1
As the deployment of deep learning models continues to expand across industries, the threat of malicious incursions aimed at gaining access to these deployed models is on the rise.…
NetDiffusion: Network Data Augmentation Through Protocol-Constrained Traffic Generation
Xi Jiang, Shinan Liu, Aaron Gember-Jacobson +4
Datasets of labeled network traces are essential for a multitude of machine learning (ML) tasks in networking, yet their availability is hindered by privacy and maintenance concern…
Characterizing the Optimal 0-1 Loss for Multi-class Classification with a Test-time Attacker
Sihui Dai, Wenxin Ding, Arjun Nitin Bhagoji +4
Finding classifiers robust to adversarial examples is critical for their safe deployment. Determining the robustness of the best possible classifier under a given threat model for…
Augmenting Rule-based DNS Censorship Detection at Scale with Machine Learning
Jacob Brown, Xi Jiang, Van Tran +5
The proliferation of global censorship has led to the development of a plethora of measurement platforms to monitor and expose it. Censorship of the domain name system (DNS) is a k…
Natural Backdoor Datasets
Emily Wenger, Roma Bhattacharjee, Arjun Nitin Bhagoji +4
Extensive literature on backdoor poison attacks has studied attacks and defenses for backdoors using "digital trigger patterns." In contrast, "physical backdoors" use physical obje…
Understanding Robust Learning through the Lens of Representation Similarities
Christian Cianfarani, Arjun Nitin Bhagoji, Vikash Sehwag +3
Representation learning, i.e. the generation of representations useful for downstream applications, is a task of fundamental importance that underlies much of the success of deep n…
On the Permanence of Backdoors in Evolving Models
Huiying Li, Arjun Nitin Bhagoji, Yuxin Chen +2
Existing research on training-time attacks for deep neural networks (DNNs), such as backdoors, largely assume that models are static once trained, and hidden backdoors trained into…
SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification
Ashwinee Panda, Saeed Mahloujifar, Arjun N. Bhagoji +2
Federated learning is inherently vulnerable to model poisoning attacks because its decentralized nature allows attackers to participate with compromised devices. In model poisoning…
Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networks
Shawn Shan, Arjun Nitin Bhagoji, Haitao Zheng +1
In adversarial machine learning, new defenses against attacks on deep learning systems are routinely broken soon after their release by more powerful attacks. In this context, fore…
LEAF: Navigating Concept Drift in Cellular Networks
Shinan Liu, Francesco Bronzino, Paul Schmitt +5
Operational networks commonly rely on machine learning models for many tasks, including detecting anomalies, inferring application performance, and forecasting demand. Yet, model a…
Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries
Arjun Nitin Bhagoji, Daniel Cullina, Vikash Sehwag +1
Understanding the fundamental limits of robust supervised learning has emerged as a problem of immense interest, from both practical and theoretical standpoints. In particular, it…
A Real-time Defense against Website Fingerprinting Attacks
Shawn Shan, Arjun Nitin Bhagoji, Haitao Zheng +1
Anonymity systems like Tor are vulnerable to Website Fingerprinting (WF) attacks, where a local passive eavesdropper infers the victim's activity. Current WF attacks based on deep…
A Critical Evaluation of Open-World Machine Learning
Liwei Song, Vikash Sehwag, Arjun Nitin Bhagoji +1
Open-world machine learning (ML) combines closed-world models trained on in-distribution data with out-of-distribution (OOD) detectors, which aim to detect and reject OOD inputs. P…
Backdoor Attacks Against Deep Learning Systems in the Physical World
Emily Wenger, Josephine Passananti, Arjun Bhagoji +3
Backdoor attacks embed hidden malicious behaviors into deep learning models, which only activate and cause misclassifications on model inputs containing a specific trigger. Existin…
PatchGuard: A Provably Robust Defense against Adversarial Patches via Small Receptive Fields and Masking
Chong Xiang, Arjun Nitin Bhagoji, Vikash Sehwag +1
Localized adversarial patches aim to induce misclassification in machine learning models by arbitrarily modifying pixels within a restricted region of an image. Such attacks can be…
Advances and Open Problems in Federated Learning
Peter Kairouz, H. Brendan McMahan, Brendan Avent +56
Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a cen…