Demo Data from SIGIR 2026 / reviewers in the wild / expert
Sasha Behrouzi
dblp:364/6660
· DBLP profile ↗
3ranked-venue papers
0as first author
3since 2021 · last 2026
—ORCID · none
Domains — the database's venue-derived domains; a paper can count in several
Security and privacy · 3 · 3 since 2021
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Network and information security
3 papers |
Digital forensics and information hiding · 47% Security and privacy of machine learning · 32% Privacy and data protection · 22% | |
| Artificial intelligence
1 paper |
Language models and text generation · 100% |
Topics — the 6 heaviest of 6, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Security and privacy of machine learning › large language model security
adversarial attacks on language models |
1.0 | 1 | 2026 | NeuroStrike: Neuron-Level Attacks on Aligned LLMs · NDSS 2026 |
Digital forensics and information hiding
deepfake detection |
1.0 | 1 | 2026 | Light2Lie: Detecting Deepfake Images Using Physical Reflectance Laws · NDSS 2026 |
Digital forensics and information hiding › copyright protection
image copyright protection |
0.9 | 1 | 2025 | LightShed: Defeating Perturbation-based Image Copyright Protections · USENIX Security Symposium 2025 |
Privacy and data protection › statistical database privacy
perturbation-based protection |
0.9 | 1 | 2025 | LightShed: Defeating Perturbation-based Image Copyright Protections · USENIX Security Symposium 2025 |
Natural language and speech › Language models and text generation › alignment
aligned large language models |
0.3 | 1 | 2026 | NeuroStrike: Neuron-Level Attacks on Aligned LLMs · NDSS 2026 |
Security and privacy of machine learning › adversarial attack
adversarial perturbation |
0.3 | 1 | 2025 | LightShed: Defeating Perturbation-based Image Copyright Protections · USENIX Security Symposium 2025 |
Methods — techniques the papers use, named apart from their topics
neuron-level perturbation · 2.0physical reflectance laws · 1.0image processing · 0.9adversarial perturbation · 0.9
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2026 | Light2Lie: Detecting Deepfake Images Using Physical Reflectance Laws
Kavita Kumari, Sasha Behrouzi, Alessandro Pegoraro, Ahmad-Reza Sadeghi |
NDSS | 2 |
| 2026 | NeuroStrike: Neuron-Level Attacks on Aligned LLMs
Lichao Wu, Sasha Behrouzi, Mohamadreza Rostami, Maximilian Thang, Stjepan Picek, Ahmad-Reza Sadeghi |
NDSS | 2 |
| 2025 | LightShed: Defeating Perturbation-based Image Copyright Protections
Hanna Foerster, Sasha Behrouzi, Phillip Rieger, Murtuza Jadliwala, Ahmad-Reza Sadeghi |
USENIX Security Symposium | 2 |