90 citations · 94 across the 7 of their papers we have counts for
8 papers
Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy
Gauri Pradhan, Joonas Jälkö, Santiago Zanella-Béguelin +1
Training machine learning models with differential privacy (DP) limits an adversary's ability to infer sensitive information about the training data. It can be interpreted as a bou…
A Systematization of Security Vulnerabilities in Computer Use Agents
Daniel Jones, Giorgio Severi, Martin Pouliot +7
Computer Use Agents (CUAs), autonomous systems that interact with software interfaces via browsers or virtual machines, are rapidly being deployed in consumer and enterprise enviro…
A Representation Engineering Perspective on the Effectiveness of Multi-Turn Jailbreaks
Blake Bullwinkel, Mark Russinovich, Ahmed Salem +8
Recent research has demonstrated that state-of-the-art LLMs and defenses remain susceptible to multi-turn jailbreak attacks. These attacks require only closed-box model access and…
Permissive Information-Flow Analysis for Large Language Models
Shoaib Ahmed Siddiqui, Radhika Gaonkar, Boris Köpf +7
Large Language Models (LLMs) are rapidly becoming commodity components of larger software systems. This poses natural security and privacy problems: poisoned data retrieved from on…
Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
Edoardo Debenedetti, Javier Rando, Daniel Paleka +18
Large language model systems face important security risks from maliciously crafted messages that aim to overwrite the system's original instructions or leak private data. To study…
Closed-Form Bounds for DP-SGD against Record-level Inference
Giovanni Cherubin, Boris Köpf, Andrew Paverd +3
Machine learning models trained with differentially-private (DP) algorithms such as DP-SGD enjoy resilience against a wide range of privacy attacks. Although it is possible to deri…
On the Efficacy of Differentially Private Few-shot Image Classification
Marlon Tobaben, Aliaksandra Shysheya, John Bronskill +5
There has been significant recent progress in training differentially private (DP) models which achieve accuracy that approaches the best non-private models. These DP models are ty…
Analyzing Information Leakage of Updates to Natural Language Models
Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople +5
To continuously improve quality and reflect changes in data, machine learning applications have to regularly retrain and update their core models. We show that a differential analy…