733 citations · 957 across the 15 of their papers we have counts for
16 papers
Rerouting LLM Routers
Avital Shafran, Roei Schuster, Thomas Ristenpart +1
LLM routers aim to balance quality and cost of generation by classifying queries and routing them to a cheaper or more expensive LLM depending on their complexity. Routers represen…
Mitigating Trauma in Qualitative Research Infrastructure: Roles for Machine Assistance and Trauma-Informed Design
Emily Tseng, Thomas Ristenpart, Nicola Dell
Researchers increasingly look to understand experiences of pain, harm, and marginalization via qualitative analysis. Such work is needed to understand and address social ills, but…
SoK: Safer Digital-Safety Research Involving At-Risk Users
Rosanna Bellini, Emily Tseng, Noel Warford +9
Research involving at-risk users -- that is, users who are more likely to experience a digital attack or to be disproportionately affected when harm from such an attack occurs -- c…
Characterizing Alternative Monetization Strategies on YouTube
Yiqing Hua, Manoel Horta Ribeiro, Robert West +2
One of the key emerging roles of the YouTube platform is providing creators the ability to generate revenue from their content and interactions. Alongside tools provided directly b…
Increasing Adversarial Uncertainty to Scale Private Similarity Testing
Yiqing Hua, Armin Namavari, Kaishuo Cheng +2
Social media and other platforms rely on automated detection of abusive content to help combat disinformation, harassment, and abuse. One common approach is to check user content f…
Might I Get Pwned: A Second Generation Compromised Credential Checking Service
Bijeeta Pal, Mazharul Islam, Marina Sanusi +6
Credential stuffing attacks use stolen passwords to log into victim accounts. To defend against these attacks, recently deployed compromised credential checking (C3) services provi…
Guarding Serverless Applications with SecLambda
Deepak Sirone Jegan, Liang Wang, Siddhant Bhagat +2
As an emerging application paradigm, serverless computing attracts attention from more and more attackers. Unfortunately, security tools for conventional applications cannot be eas…
The Tools and Tactics Used in Intimate Partner Surveillance: An Analysis of Online Infidelity Forums
Emily Tseng, Rosanna Bellini, Nora McDonald +5
Abusers increasingly use spyware apps, account compromise, and social engineering to surveil their intimate partners, causing substantial harms that can culminate in violence. This…
Characterizing Twitter Users Who Engage in Adversarial Interactions against Political Candidates
Yiqing Hua, Mor Naaman, Thomas Ristenpart
Social media provides a critical communication platform for political figures, but also makes them easy targets for harassment. In this paper, we characterize users who adversarial…
Towards Measuring Adversarial Twitter Interactions against Candidates in the US Midterm Elections
Yiqing Hua, Thomas Ristenpart, Mor Naaman
Adversarial interactions against politicians on social media such as Twitter have significant impact on society. In particular they disrupt substantive political discussions online…
Protocols for Checking Compromised Credentials
Lucy Li, Bijeeta Pal, Junade Ali +3
To prevent credential stuffing attacks, industry best practice now proactively checks if user credentials are present in known data breaches. Recently, some web services, such as H…
When Textbook RSA is Used to Protect the Privacy of Hundreds of Millions of Users
Jeffrey Knockel, Thomas Ristenpart, Jedidiah Crandall
We evaluate Tencent's QQ Browser, a popular mobile browser in China with hundreds of millions of users---including 16 million overseas, with respect to the threat model of a man-in…
Machine Learning Models that Remember Too Much
Congzheng Song, Thomas Ristenpart, Vitaly Shmatikov
Machine learning (ML) is becoming a commodity. Numerous ML frameworks and services are available to data holders who are not ML experts but want to train predictive models on their…
Stealing Machine Learning Models via Prediction APIs
Florian Tramèr, Fan Zhang, Ari Juels +2
Machine learning (ML) models may be deemed confidential due to their sensitive training data, commercial value, or use in security applications. Increasingly often, confidential ML…
Network Traffic Obfuscation and Automated Internet Censorship
Lucas Dixon, Thomas Ristenpart, Thomas Shrimpton
Internet censors seek ways to identify and block internet access to information they deem objectionable. Increasingly, censors deploy advanced networking tools such as deep-packet…
A Placement Vulnerability Study in Multi-tenant Public Clouds
Venkatanathan Varadarajan, Yinqian Zhang, Thomas Ristenpart +1
Public infrastructure-as-a-service clouds, such as Amazon EC2, Google Compute Engine (GCE) and Microsoft Azure allow clients to run virtual machines (VMs) on shared physical infras…