1 citations · 1 across the 5 of their papers we have counts for
5 papers
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…
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…
No offence, Bert -- I insult only humans! Multiple addressees sentence-level attack on toxicity detection neural network
Sergey Berezin, Reza Farahbakhsh, Noel Crespi
We introduce a simple yet efficient sentence-level attack on black-box toxicity detector models. By adding several positive words or sentences to the end of a hateful message, we a…
On the definition of toxicity in NLP
Sergey Berezin, Reza Farahbakhsh, Noel Crespi
The fundamental problem in toxicity detection task lies in the fact that the toxicity is ill-defined. This causes us to rely on subjective and vague data in models' training, which…
Neural arbitrary style transfer for portrait images using the attention mechanism
S. A. Berezin, V. M. Volkova
Arbitrary style transfer is the task of synthesis of an image that has never been seen before, using two given images: content image and style image. The content image forms the st…