90 citations · 118 across the 9 of their papers we have counts for
13 papers
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…
Maatphor: Automated Variant Analysis for Prompt Injection Attacks
Ahmed Salem, Andrew Paverd, Boris Köpf
Prompt injection has emerged as a serious security threat to large language models (LLMs). At present, the current best-practice for defending against newly-discovered prompt injec…
Hide and Seek with Spectres: Efficient discovery of speculative information leaks with random testing
Oleksii Oleksenko, Marco Guarnieri, Boris Köpf +1
Attacks like Spectre abuse speculative execution, one of the key performance optimizations of modern CPUs. Recently, several testing tools have emerged to automatically detect spec…
Revizor: Testing Black-box CPUs against Speculation Contracts
Oleksii Oleksenko, Christof Fetzer, Boris Köpf +1
Speculative vulnerabilities such as Spectre and Meltdown expose speculative execution state that can be exploited to leak information across security domains via side-channels. Suc…
CacheQuery: Learning Replacement Policies from Hardware Caches
Pepe Vila, Pierre Ganty, Marco Guarnieri +1
We show how to infer deterministic cache replacement policies using off-the-shelf automata learning and program synthesis techniques. For this, we construct and chain two abstracti…
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…
SPECTECTOR: Principled Detection of Speculative Information Flows
Marco Guarnieri, Boris Köpf, José F. Morales +2
Since the advent of SPECTRE, a number of countermeasures have been proposed and deployed. Rigorously reasoning about their effectiveness, however, requires a well-defined notion of…
Theory and Practice of Finding Eviction Sets
Pepe Vila, Boris Köpf, José Francisco Morales
Many micro-architectural attacks rely on the capability of an attacker to efficiently find small eviction sets: groups of virtual addresses that map to the same cache set. This cap…
On the Incomparability of Cache Algorithms in Terms of Timing Leakage
Pablo Cañones, Boris Köpf, Jan Reineke
Modern computer architectures rely on caches to reduce the latency gap between the CPU and main memory. While indispensable for performance, caches pose a serious threat to securit…
Loophole: Timing Attacks on Shared Event Loops in Chrome
Pepe Vila, Boris Köpf
Event-driven programming (EDP) is the prevalent paradigm for graphical user interfaces, web clients, and it is rapidly gaining importance for server-side and network programming. C…
Security Analysis of Cache Replacement Policies
Pablo Cañones, Boris Köpf, Jan Reineke
Modern computer architectures share physical resources between different programs in order to increase area-, energy-, and cost-efficiency. Unfortunately, sharing often gives rise…
A Language-theoretic View on Network Protocols
Pierre Ganty, Boris Köpf, Pedro Valero
Input validation is the first line of defense against malformed or malicious inputs. It is therefore critical that the validator (which is often part of the parser) is free of bugs…
Rigorous Analysis of Software Countermeasures against Cache Attacks
Goran Doychev, Boris Köpf
CPU caches introduce variations into the execution time of programs that can be exploited by adversaries to recover private information about users or cryptographic keys. Establish…