Search Results for author:
Found 12 papers, 2 papers with code
The SpongeNet Attack: Sponge Weight Poisoning of Deep Neural Networks
SpongeNet is the first sponge attack that is performed directly on the parameters of a pre-trained model.
Dr. Jekyll and Mr. Hyde: Two Faces of LLMs
This work shows that by using adversarial personas, one can overcome safety mechanisms set out by ChatGPT and Bard.
Tabdoor: Backdoor Vulnerabilities in Transformer-based Neural Networks for Tabular Data
Our findings highlight the urgency of addressing such vulnerabilities and provide insights into potential countermeasures for securing DNN models against backdoors in tabular data.
Invisible Threats: Backdoor Attack in OCR Systems
Optical Character Recognition (OCR) is a widely used tool to extract text from scanned documents.
Label Inference Attacks against Node-level Vertical Federated GNNs
In this work, we are the first (to the best of our knowledge) to investigate label inference attacks on VFL using a zero-background knowledge strategy.
Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Sound
Motivated by these findings, we propose to exploit elements of sound ($e. g.$, pitch and timbre) to design more stealthy yet effective poison-only backdoor attacks.
SoK: A Systematic Evaluation of Backdoor Trigger Characteristics in Image Classification
Nevertheless, it is vulnerable to backdoor attacks that modify the training set to embed a secret functionality in the trained model.
Going In Style: Audio Backdoors Through Stylistic Transformations
This work explores stylistic triggers for backdoor attacks in the audio domain: dynamic transformations of malicious samples through guitar effects.
Dynamic Backdoors with Global Average Pooling
It was recently shown that countermeasures in image classification, like Neural Cleanse and ABS, could be bypassed with dynamic triggers that are effective regardless of their pattern and location.
More is Better (Mostly): On the Backdoor Attacks in Federated Graph Neural Networks
To further explore the properties of two backdoor attacks in Federated GNNs, we evaluate the attack performance for a different number of clients, trigger sizes, poisoning intensities, and trigger densities.
Watermarking Graph Neural Networks based on Backdoor Attacks
The experiments show that our framework can verify the ownership of GNN models with a very high probability (up to $99\%$) for both tasks.
Can You Hear It? Backdoor Attacks via Ultrasonic Triggers
This work explores backdoor attacks for automatic speech recognition systems where we inject inaudible triggers.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
