37 citations · 224 across the 83 of their papers we have counts for
14 papers · 1 filter
The More the Merrier: On Evolving Five-valued Spectra Boolean Functions
Claude Carlet, Marko Ðurasevic, Domagoj Jakobovic +2
Evolving Boolean functions with specific properties is an interesting optimization problem since, depending on the combination of properties and Boolean function size, the problem…
Flashy Backdoor: Real-world Environment Backdoor Attack on SNNs with DVS Cameras
Roberto Riaño, Gorka Abad, Stjepan Picek +1
While security vulnerabilities in traditional Deep Neural Networks (DNNs) have been extensively studied, the susceptibility of Spiking Neural Networks (SNNs) to adversarial attacks…
Membership Privacy Evaluation in Deep Spiking Neural Networks
Jiaxin Li, Gorka Abad, Stjepan Picek +1
Artificial Neural Networks (ANNs), commonly mimicking neurons with non-linear functions to output floating-point numbers, consistently receive the same signals of a data point duri…
EmoBack: Backdoor Attacks Against Speaker Identification Using Emotional Prosody
Coen Schoof, Stefanos Koffas, Mauro Conti +1
Speaker identification (SI) determines a speaker's identity based on their spoken utterances. Previous work indicates that SI deep neural networks (DNNs) are vulnerable to backdoor…
Context is the Key: Backdoor Attacks for In-Context Learning with Vision Transformers
Gorka Abad, Stjepan Picek, Lorenzo Cavallaro +1
Due to the high cost of training, large model (LM) practitioners commonly use pretrained models downloaded from untrusted sources, which could lead to owning compromised models. In…
Continuous Embedding Attacks via Clipped Inputs in Jailbreaking Large Language Models
Zihao Xu, Yi Liu, Gelei Deng +4
Security concerns for large language models (LLMs) have recently escalated, focusing on thwarting jailbreaking attempts in discrete prompts. However, the exploration of jailbreak v…
BAN: Detecting Backdoors Activated by Adversarial Neuron Noise
Xiaoyun Xu, Zhuoran Liu, Stefanos Koffas +2
Backdoor attacks on deep learning represent a recent threat that has gained significant attention in the research community. Backdoor defenses are mainly based on backdoor inversio…
Large Language Models are Covert Channels
Simen Gaure, Stefanos Koffas, Stjepan Picek +1
Large Language Models (LLMs) have gained significant popularity recently. LLMs are susceptible to various attacks but can also improve the security of diverse systems. However, bes…
Let's Focus: Focused Backdoor Attack against Federated Transfer Learning
Marco Arazzi, Stefanos Koffas, Antonino Nocera +1
Federated Transfer Learning (FTL) is the most general variation of Federated Learning. According to this distributed paradigm, a feature learning pre-step is commonly carried out b…
The Power of Bamboo: On the Post-Compromise Security for Searchable Symmetric Encryption
Tianyang Chen, Peng Xu, Stjepan Picek +4
Dynamic searchable symmetric encryption (DSSE) enables users to delegate the keyword search over dynamically updated encrypted databases to an honest-but-curious server without los…
A Systematic Evaluation of Evolving Highly Nonlinear Boolean Functions in Odd Sizes
Claude Carlet, Marko Ðurasevic, Domagoj Jakobovic +2
Boolean functions are mathematical objects used in diverse applications. Different applications also have different requirements, making the research on Boolean functions very acti…
Time-Distributed Backdoor Attacks on Federated Spiking Learning
Gorka Abad, Stjepan Picek, Aitor Urbieta
This paper investigates the vulnerability of spiking neural networks (SNNs) and federated learning (FL) to backdoor attacks using neuromorphic data. Despite the efficiency of SNNs…
A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models
Zihao Xu, Yi Liu, Gelei Deng +2
Large Language Models (LLMS) have increasingly become central to generating content with potential societal impacts. Notably, these models have demonstrated capabilities for genera…
The SkipSponge Attack: Sponge Weight Poisoning of Deep Neural Networks
Jona te Lintelo, Stefanos Koffas, Stjepan Picek
Sponge attacks aim to increase the energy consumption and computation time of neural networks. In this work, we present a novel sponge attack called SkipSponge. SkipSponge is the f…