Picture for Stjepan Picek

Stjepan Picek

BAN: Detecting Backdoors Activated by Adversarial Neuron Noise

May 30, 2024
Viaarxiv icon

Let's Focus: Focused Backdoor Attack against Federated Transfer Learning

Apr 30, 2024
Viaarxiv icon

LLM Jailbreak Attack versus Defense Techniques -- A Comprehensive Study

Add code
Feb 21, 2024
Viaarxiv icon

A Systematic Evaluation of Evolving Highly Nonlinear Boolean Functions in Odd Sizes

Feb 15, 2024
Viaarxiv icon

The SpongeNet Attack: Sponge Weight Poisoning of Deep Neural Networks

Add code
Feb 09, 2024
Viaarxiv icon

Time-Distributed Backdoor Attacks on Federated Spiking Learning

Feb 05, 2024
Viaarxiv icon

MIMIR: Masked Image Modeling for Mutual Information-based Adversarial Robustness

Add code
Dec 08, 2023
Figure 1 for MIMIR: Masked Image Modeling for Mutual Information-based Adversarial Robustness
Figure 2 for MIMIR: Masked Image Modeling for Mutual Information-based Adversarial Robustness
Figure 3 for MIMIR: Masked Image Modeling for Mutual Information-based Adversarial Robustness
Figure 4 for MIMIR: Masked Image Modeling for Mutual Information-based Adversarial Robustness
Viaarxiv icon

Dr. Jekyll and Mr. Hyde: Two Faces of LLMs

Add code
Dec 06, 2023
Viaarxiv icon

A New Angle: On Evolving Rotation Symmetric Boolean Functions

Nov 20, 2023
Viaarxiv icon

Look into the Mirror: Evolving Self-Dual Bent Boolean Functions

Nov 20, 2023
Viaarxiv icon