Search Results for author:
Found 26 papers, 10 papers with code
Memory Backdoor Attacks on Neural Networks
What makes this attack unique is that it (1) works even when the tasks conflict (making a classifier output images), (2) enables the systematic extraction of training samples from deployed models and (3) offers guarantees on the extracted authenticity of the data.
Efficient Model Extraction via Boundary Sampling
This paper introduces a novel data-free model extraction attack that significantly advances the current state-of-the-art in terms of efficiency, accuracy, and effectiveness.
The Best Defense is a Good Offense: Countering LLM-Powered Cyberattacks
As large language models (LLMs) continue to evolve, their potential use in automating cyberattacks becomes increasingly likely.
PEAS: A Strategy for Crafting Transferable Adversarial Examples
We then evaluate the transferability of adversarial perturbations on these images using a set of substitute models.
Are You Human? An Adversarial Benchmark to Expose LLMs
Our evaluation of 9 leading models from the LMSYS leaderboard revealed that explicit challenges successfully detected LLMs in 78. 4% of cases, while implicit challenges were effective in 22. 9% of instances.
Back-in-Time Diffusion: Unsupervised Detection of Medical Deepfakes
Recent progress in generative models has made it easier for a wide audience to edit and create image content, raising concerns about the proliferation of deepfakes, especially in healthcare.
TTTS: Tree Test Time Simulation for Enhancing Decision Tree Robustness against Adversarial Examples
Without the presence of any attacks, TTTS has successfully improved model performance from an AUC of 0. 714 to 0. 773.
Counter-Samples: A Stateless Strategy to Neutralize Black Box Adversarial Attacks
Our paper presents a novel defence against black box attacks, where attackers use the victim model as an oracle to craft their adversarial examples.
What Was Your Prompt? A Remote Keylogging Attack on AI Assistants
In this paper, we unveil a novel side-channel that can be used to read encrypted responses from AI Assistants over the web: the token-length side-channel.
Transpose Attack: Stealing Datasets with Bidirectional Training
In addition, in this work we show that neural networks can be taught to systematically memorize and retrieve specific samples from datasets.
Discussion Paper: The Threat of Real Time Deepfakes
Generative deep learning models are able to create realistic audio and video.
Deepfake CAPTCHA: A Method for Preventing Fake Calls
In this work we focus on real-time audio deepfakes and present preliminary results on video.
Transferability Ranking of Adversarial Examples
By leveraging a set of diverse surrogate models, our method can predict transferability of adversarial examples.
DF-Captcha: A Deepfake Captcha for Preventing Fake Calls
In this paper, we propose a lightweight application which can protect organizations and individuals from deepfake SE attacks.
The Security of Deep Learning Defences for Medical Imaging
Deep learning has shown great promise in the domain of medical image analysis.
The Threat of Offensive AI to Organizations
Although offensive AI has been discussed in the past, there is a need to analyze and understand the threat in the context of organizations.
IPatch: A Remote Adversarial Patch
In this paper, we introduce a new type of adversarial patch which alters a model's perception of an image's semantics.
Lightweight Collaborative Anomaly Detection for the IoT using Blockchain
Due to their rapid growth and deployment, the Internet of things (IoT) have become a central aspect of our daily lives.
The Creation and Detection of Deepfakes: A Survey
Generative deep learning algorithms have progressed to a point where it is difficult to tell the difference between what is real and what is fake.
DANTE: A framework for mining and monitoring darknet traffic
In this paper, we present DANTE: a framework and algorithm for mining darknet traffic.
Physical Layer Encryption using a Vernam Cipher
In this paper, we present the Vernam Physical Signal Cipher (VPSC): a novel cipher which can encrypt the harmonic composition of any analog waveform.
Cryptography and Security
Online Budgeted Learning for Classifier Induction
In online learning, the challenge is to find the optimum set of features to be acquired from each instance upon arrival from a data stream.
CT-GAN: Malicious Tampering of 3D Medical Imagery using Deep Learning
In this paper, we show how an attacker can use deep-learning to add or remove evidence of medical conditions from volumetric (3D) medical scans.
N-BaIoT: Network-based Detection of IoT Botnet Attacks Using Deep Autoencoders
The proliferation of IoT devices which can be more easily compromised than desktop computers has led to an increase in the occurrence of IoT based botnet attacks.
CIoTA: Collaborative IoT Anomaly Detection via Blockchain
However, an anomaly detection model must be trained for a long time in order to capture all benign behaviors.
Kitsune: An Ensemble of Autoencoders for Online Network Intrusion Detection
In this paper, we present Kitsune: a plug and play NIDS which can learn to detect attacks on the local network, without supervision, and in an efficient online manner.
