3 papers
cs.LG2026
Toxicity Detection Should Measure Contextual Harm, Not Text-Intrinsic Badness
Sergei Berezin, Reza Farahbakhsh, Noel Crespi
Toxicity detection has become core safety infrastructure for online moderation, dataset filtering, and deployed language-model systems. Yet most detectors still treat toxicity as a…
cs.CL2025
Evading Toxicity Detection with ASCII-art: A Benchmark of Spatial Attacks on Moderation Systems
Sergey Berezin, Reza Farahbakhsh, Noel Crespi
We introduce a novel class of adversarial attacks on toxicity detection models that exploit language models' failure to interpret spatially structured text in the form of ASCII art…
cs.CR2025
The TIP of the Iceberg: Revealing a Hidden Class of Task-in-Prompt Adversarial Attacks on LLMs
Sergey Berezin, Reza Farahbakhsh, Noel Crespi
We present a novel class of jailbreak adversarial attacks on LLMs, termed Task-in-Prompt (TIP) attacks. Our approach embeds sequence-to-sequence tasks (e.g., cipher decoding, riddl…