Michael Backes
where else to find them
no profile links on file
what they talk about
all 4 in the filters
where they keep going back
no series more than once — all 7 in the filters
on a stage with
all 30 in the filters
who talks about the same things
- Marco Patrignani14 talks
- Katharina Krombholz11 talks
- Nicolas Huaman4 talks
- Niklas Mück3 talks
- Michael Schwarz25 talks
- Yasemin Acar11 talks
| title | conference | date |
|---|---|---|
| SoK: Data Reconstruction Attacks Against Machine Learning Models... | USENIX Security '25 | 2025-08-13 |
Provides a formal definition and taxonomy for vision-domain data reconstruction, plus a benchmark that evaluates 10 attacks on models trained with 100–20,000… | ||
| Do You Even Lift? Strengthening Compiler Security Guarantees Against Spectre Attacks | POPL 2025 | 2025-01-19 |
Paper introduces a lifting framework that upgrades compiler guarantees proved for weaker speculative semantics to stronger ones without redoing full secure… | ||
| Lifting Compiler Security Properties to Stronger Attackers: the Speculation Cas... | PriSC 2024 | 2024-01-20 |
A formal framework proves when a compiler countermeasure for Spectre-style leaks preserves security against stronger attacker models by modelling speculative… | ||
| Secure Composition of SPECTRE Mitigations | PriSC 2024 | 2024-01-20 |
Formal framework proves when compiler passes that add Spectre mitigations compose safely and when they do not, using robust preservation and a cross-language… | ||
| Industrial practitioners' mental models of adversarial machine learning | SOUPS 2022 | 2022-08-07 |
Qualitative study of 15 interviews with European startup practitioners in 2020 uses semi-structured interviews plus a whiteboard drawing task and thematic… | ||
| Studying the Impact of Managers on Password Strength and Reuse | USENIX Security '18 | 2018-08-15 |
Large-scale study combines 476 survey participants with 170 browser-plugin users to measure real passwords (average 10 accounts, 6 distinct passwords)… | ||
| How the Web Tangled Itself | 26th USENIX Security Symposium (USENIX Security '17) | 2017-08-16 |
Analysis of Internet Archive snapshots (1997–2016) inspects 659,710 documents, 1.4M frames, 5M scripts and 21M HTTP headers to track client-side security… | ||
| What Cannot Be Read, Cannot Be Leveraged? Revisiting Assumptions of JIT-ROP... | USENIX Security '16 | 2016-08-10 |
Demonstrates that JIT-ROP does not need readable code: a JIT compiler is coerced to emit arbitrary three-byte gadgets by controlling displacement fields in… | ||
| Hey, You Have a Problem: On the Feasibility of Large-Scale Web Vulnerability | USENIX Security '16 | 2016-08-10 |
Study scans the Alexa top million and finds 44,000 vulnerable domains (WordPress and site-specific DOM XSS), splits them into five groups, and sends targeted… | ||
| On Demystifying the Android Application Framework: Re-Visiting Android... | USENIX Security '16 | 2016-08-10 |
A static-analysis pipeline builds a runtime model of Android’s framework, enumerates binder entry points, and models handler/channel/state-machine concurrency… | ||
| Privacy in Epigenetics: Temporal Linkability of MicroRNA Expression Profiles | USENIX Security '16 | 2016-08-10 |
Paper shows blood-based miRNA profiles are linkable over time: an identification attack reaches ~76% success on blood (≈30% plasma), while a global matching… | ||
| nothing matches | ||