activity
20242026
most citedGeopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models

2 citations · 2 across the 6 of their papers we have counts for

collaborators

13 papers

cs.CR2026

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…

cs.SD2026

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…

cs.LG2026

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…

cs.CL2025

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…

cs.LG2025

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…

cs.LG2025

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…