activity
20242026
collaborators

5 papers

cs.CR2026

Evaluating Concept Filtering Defenses against Child Sexual Abuse Material Generation by Text-to-Image Models

Ana-Maria Cretu, Klim Kireev, Amro Abdalla +5

We evaluate the effectiveness of filtering child images from training datasets of text-to-image models to prevent model misuse to create child sexual abuse material (CSAM). First,…

cs.CV2025

A Manually Annotated Image-Caption Dataset for Detecting Children in the Wild

Klim Kireev, Ana-Maria Creţu, Raphael Meier +3

Platforms and the law regulate digital content depicting minors (defined as individuals under 18 years of age) differently from other types of content. Given the sheer amount of co…

cs.SI2024

Characterizing and Detecting Propaganda-Spreading Accounts on Telegram

Klim Kireev, Yevhen Mykhno, Carmela Troncoso +1

Information-based attacks on social media, such as disinformation campaigns and propaganda, are emerging cybersecurity threats. The security community has focused on countering the…

cs.CR2024

SINBAD: Saliency-informed detection of breakage caused by ad blocking

Saiid El Hajj Chehade, Sandra Siby, Carmela Troncoso

Privacy-enhancing blocking tools based on filter-list rules tend to break legitimate functionality. Filter-list maintainers could benefit from automated breakage detection tools th…

cs.CR2024

Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks

Dario Pasquini, Martin Strohmeier, Carmela Troncoso

We introduce a new family of prompt injection attacks, termed Neural Exec. Unlike known attacks that rely on handcrafted strings (e.g., "Ignore previous instructions and..."), we s…