37 citations · 56 across the 19 of their papers we have counts for
14 papers · 1 filter
Backdoor Attacks on Decentralised Post-Training
Oğuzhan Ersoy, Nikolay Blagoev, Jona te Lintelo +3
Decentralised post-training of large language models utilises data and pipeline parallelism techniques to split the data and the model. Unfortunately, decentralised post-training c…
SoK: The Last Line of Defense: On Backdoor Defense Evaluation
Gorka Abad, Marina Krček, Stefanos Koffas +7
Backdoor attacks pose a significant threat to deep learning models by implanting hidden vulnerabilities that can be activated by malicious inputs. While numerous defenses have been…
Towards Backdoor Stealthiness in Model Parameter Space
Xiaoyun Xu, Zhuoran Liu, Stefanos Koffas +1
Recent research on backdoor stealthiness focuses mainly on indistinguishable triggers in input space and inseparable backdoor representations in feature space, aiming to circumvent…
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…
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…
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…
Dr. Jekyll and Mr. Hyde: Two Faces of LLMs
Matteo Gioele Collu, Tom Janssen-Groesbeek, Stefanos Koffas +2
Large Language Models (LLMs) are being integrated into applications such as chatbots or email assistants. To prevent improper responses, safety mechanisms, such as Reinforcement Le…
Backdoor Attacks on Transformers for Tabular Data: An Empirical Study
Bart Pleiter, Behrad Tajalli, Stefanos Koffas +4
Deep Neural Networks (DNNs) have shown great promise in various domains. However, vulnerabilities associated with DNN training, such as backdoor attacks, are a significant concern.…
On the Effect of Clock Frequency on Voltage and Electromagnetic Fault Injection
Stefanos Koffas, Praveen Kumar Vadnala
We investigate the influence of clock frequency on the success rate of a fault injection attack. In particular, we examine the success rate of voltage and electromagnetic fault att…
Invisible Threats: Backdoor Attack in OCR Systems
Mauro Conti, Nicola Farronato, Stefanos Koffas +2
Optical Character Recognition (OCR) is a widely used tool to extract text from scanned documents. Today, the state-of-the-art is achieved by exploiting deep neural networks. Howeve…
Going In Style: Audio Backdoors Through Stylistic Transformations
Stefanos Koffas, Luca Pajola, Stjepan Picek +1
This work explores stylistic triggers for backdoor attacks in the audio domain: dynamic transformations of malicious samples through guitar effects. We first formalize stylistic tr…
Dynamic Backdoors with Global Average Pooling
Stefanos Koffas, Stjepan Picek, Mauro Conti
Outsourced training and machine learning as a service have resulted in novel attack vectors like backdoor attacks. Such attacks embed a secret functionality in a neural network act…
More is Better (Mostly): On the Backdoor Attacks in Federated Graph Neural Networks
Jing Xu, Rui Wang, Stefanos Koffas +2
Graph Neural Networks (GNNs) are a class of deep learning-based methods for processing graph domain information. GNNs have recently become a widely used graph analysis method due t…
Can You Hear It? Backdoor Attacks via Ultrasonic Triggers
Stefanos Koffas, Jing Xu, Mauro Conti +1
This work explores backdoor attacks for automatic speech recognition systems where we inject inaudible triggers. By doing so, we make the backdoor attack challenging to detect for…