4 citations · 10 across the 20 of their papers we have counts for
20 papers
Large Audio Language Models for Spoofing-Aware Speaker Verification
Sofya Savelyeva, Mariia Perunova, Evgeny Kushnir +3
Recent advances in text-to-speech and voice cloning make high-quality spoofing inexpensive and scalable, threatening voice authentication systems, especially automatic speaker veri…
LLM-Guided Program Evolution for Targeted Black-Box Attacks on Perceptual Hash Algorithms
A. Krylov, D. Rakhov, V. Veselova +2
Perceptual hash algorithms (PHAs) are widely deployed to detect image forgery under benign transformations, yet their robustness against adversarially chosen perturbations remains…
LLM-Guided Prompt Evolution for Password Guessing
Vladimir A. Mazin, Mikhail A. Zorin, Dmitrii S. Korzh +3
Passwords still remain a dominant authentication method, yet their security is routinely subverted by predictable user choices and large-scale credential leaks. Automated password…
Probabilistic Verification of Voice Anti-Spoofing Models
Evgeny Kushnir, Alexandr Kozodaev, Dmitrii Korzh +3
Recent advances in generative models have amplified the risk of malicious misuse of speech synthesis technologies, enabling adversaries to impersonate target speakers and access se…
Towards Robust Speech Deepfake Detection via Human-Inspired Reasoning
Artem Dvirniak, Evgeny Kushnir, Dmitrii Tarasov +5
The modern generative audio models can be used by an adversary in an unlawful manner, specifically, to impersonate other people to gain access to private information. To mitigate t…
Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?
Anton Korznikov, Andrey Galichin, Alexey Dontsov +3
Sparse Autoencoders (SAEs) have emerged as a promising tool for interpreting neural networks by decomposing their activations into sparse sets of human-interpretable features. Rece…
Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs
Nikita Afonin, Nikita Andriianov, Vahagn Hovhannisyan +9
Recent work has shown that narrow finetuning can produce broadly misaligned LLMs, a phenomenon termed emergent misalignment (EM). While concerning, these findings were limited to f…
OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features
Anton Korznikov, Andrey Galichin, Alexey Dontsov +3
Sparse autoencoders (SAEs) are a technique for sparse decomposition of neural network activations into human-interpretable features. However, current SAEs suffer from feature absor…
The Rogue Scalpel: Activation Steering Compromises LLM Safety
Anton Korznikov, Andrey Galichin, Alexey Dontsov +3
Activation steering is a promising technique for controlling LLM behavior by adding semantically meaningful vectors directly into a model's hidden states during inference. It is of…
HAMSA: Hijacking Aligned Compact Models via Stealthy Automation
Alexey Krylov, Iskander Vagizov, Dmitrii Korzh +6
Large Language Models (LLMs), especially their compact efficiency-oriented variants, remain susceptible to jailbreak attacks that can elicit harmful outputs despite extensive align…
Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences
Dmitrii Korzh, Dmitrii Tarasov, Artyom Iudin +6
Conversion of spoken mathematical expressions is a challenging task that involves transcribing speech into a strictly structured symbolic representation while addressing the ambigu…
Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models
Mikhail Salnikov, Dmitrii Korzh, Ivan Lazichny +7
This paper evaluates geopolitical biases in LLMs with respect to various countries though an analysis of their interpretation of historical events with conflicting national perspec…
Novel Loss-Enhanced Universal Adversarial Patches for Sustainable Speaker Privacy
Elvir Karimov, Alexander Varlamov, Danil Ivanov +2
Deep learning voice models are commonly used nowadays, but the safety processing of personal data, such as human identity and speech content, remains suspicious. To prevent malicio…
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
Andrey Galichin, Alexey Dontsov, Polina Druzhinina +4
Recent LLMs like DeepSeek-R1 have demonstrated state-of-the-art performance by integrating deep thinking and complex reasoning during generation. However, the internal mechanisms b…
Spread them Apart: Towards Robust Watermarking of Generated Content
Mikhail Pautov, Danil Ivanov, Andrey V. Galichin +2
Generative models that can produce realistic images have improved significantly in recent years. The quality of the generated content has increased drastically, so sometimes it is…
CLEAR: Character Unlearning in Textual and Visual Modalities
Alexey Dontsov, Dmitrii Korzh, Alexey Zhavoronkin +6
Machine Unlearning (MU) is critical for removing private or hazardous information from deep learning models. While MU has advanced significantly in unimodal (text or vision) settin…
AASIST3: KAN-Enhanced AASIST Speech Deepfake Detection using SSL Features and Additional Regularization for the ASVspoof 2024 Challenge
Kirill Borodin, Vasiliy Kudryavtsev, Dmitrii Korzh +4
Automatic Speaker Verification (ASV) systems, which identify speakers based on their voice characteristics, have numerous applications, such as user authentication in financial tra…
GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation
Andrey V. Galichin, Mikhail Pautov, Alexey Zhavoronkin +2
While Deep Neural Networks (DNNs) have demonstrated remarkable performance in tasks related to perception and control, there are still several unresolved concerns regarding the pri…
Certification of Speaker Recognition Models to Additive Perturbations
Dmitrii Korzh, Elvir Karimov, Mikhail Pautov +2
Speaker recognition technology is applied to various tasks, from personal virtual assistants to secure access systems. However, the robustness of these systems against adversarial…
Probabilistically Robust Watermarking of Neural Networks
Mikhail Pautov, Nikita Bogdanov, Stanislav Pyatkin +2
As deep learning (DL) models are widely and effectively used in Machine Learning as a Service (MLaaS) platforms, there is a rapidly growing interest in DL watermarking techniques t…