activity
20172026
most citedAUTOLYCUS: Exploiting Explainable AI (XAI) for Model Extraction Attacks against Interpretable Models

12 citations · 21 across the 14 of their papers we have counts for

collaborators
Showing cs.CRShow all

6 papers · 1 filter

cs.CR2026

SoK: Privacy Attacks on Machine Learning via Explainable AI

Abdullah Caglar Oksuz, Anisa Halimi, Erman Ayday

Machine learning explanations reveal model behavior beyond predictions, creating attack surfaces for model confidentiality and data privacy. We systematize 25 studies that exploit…

cs.CR2026

Persona-Conditioned Adversarial Prompting (PCAP): Multi-Identity Red-Teaming for Enhanced Adversarial Prompt Discovery

Cristian Morasso, Anisa Halimi, Muhammad Zaid Hameed +1

Existing automated red-teaming pipelines often miss attacks that depend on attacker identity, framing, or multi-turn tactics. This under-coverage underestimates real-world risk. We…

cs.CR2024

Towards a Re-evaluation of Data Forging Attacks in Practice

Mohamed Suliman, Anisa Halimi, Swanand Kadhe +2

Data forging attacks provide counterfactual proof that a model was trained on a given dataset, when in fact, it was trained on another. These attacks work by forging (replacing) mi…

cs.CR2022★ 3 cited

Facilitating Federated Genomic Data Analysis by Identifying Record Correlations while Ensuring Privacy

Leonard Dervishi, Xinyue Wang, Wentao Li +4

With the reduction of sequencing costs and the pervasiveness of computing devices, genomic data collection is continually growing. However, data collection is highly fragmented and…

cs.CR2020

Efficient Quantification of Profile Matching Risk in Social Networks

Anisa Halimi, Erman Ayday

Anonymous data sharing has been becoming more challenging in today's interconnected digital world, especially for individuals that have both anonymous and identified online activit…

cs.CR2017★ 6 cited

Profile Matching Across Unstructured Online Social Networks: Threats and Countermeasures

Anisa Halimi, Erman Ayday

In this work, we propose a profile matching (or deanonymization) attack for unstructured online social networks (OSNs) in which similarity in graphical structure cannot be used for…