1.5k citations · 2.3k across the 133 of their papers we have counts for
23 papers · 1 filter
Provably Protecting Fine-Tuned LLMs from Training Data Extraction while Preserving Utility
Tom Segal, Asaf Shabtai, Yuval Elovici
Fine-tuning large language models (LLMs) on sensitive datasets raises privacy concerns, as training data extraction (TDE) attacks can expose highly confidential information. Existi…
Training-Free Policy Violation Detection via Activation-Space Whitening in LLMs
Oren Rachmil, Avishag Shapira, Roy Betser +5
As organizations increasingly deploy LLMs in sensitive domains such as legal, financial, and medical settings, ensuring alignment with internal organizational policies has become a…
FRAME : Comprehensive Risk Assessment Framework for Adversarial Machine Learning Threats
Avishag Shapira, Simon Shigol, Asaf Shabtai
The widespread adoption of machine learning (ML) systems increased attention to their security and emergence of adversarial machine learning (AML) techniques that exploit fundament…
VAULT: Vigilant Adversarial Updates via LLM-Driven Retrieval-Augmented Generation for NLI
Roie Kazoom, Ofir Cohen, Rami Puzis +2
We introduce VAULT, a fully automated adversarial RAG pipeline that systematically uncovers and remedies weaknesses in NLI models through three stages: retrieval, adversarial gener…
Addressing Key Challenges of Adversarial Attacks and Defenses in the Tabular Domain: A Methodological Framework for Coherence and Consistency
Yael Itzhakev, Amit Giloni, Yuval Elovici +1
Machine learning models trained on tabular data are vulnerable to adversarial attacks, even in realistic scenarios where attackers only have access to the model's outputs. Since ta…
DOMBA: Double Model Balancing for Access-Controlled Language Models via Minimum-Bounded Aggregation
Tom Segal, Asaf Shabtai, Yuval Elovici
The utility of large language models (LLMs) depends heavily on the quality and quantity of their training data. Many organizations possess large data corpora that could be leverage…
Prompted Contextual Vectors for Spear-Phishing Detection
Daniel Nahmias, Gal Engelberg, Dan Klein +1
Spear-phishing attacks present a significant security challenge, with large language models (LLMs) escalating the threat by generating convincing emails and facilitating target rec…
CADeSH: Collaborative Anomaly Detection for Smart Homes
Yair Meidan, Dan Avraham, Hanan Libhaber +1
Although home IoT (Internet of Things) devices are typically plain and task oriented, the context of their daily use may affect their traffic patterns. For this reason, anomaly-bas…
Latent SHAP: Toward Practical Human-Interpretable Explanations
Ron Bitton, Alon Malach, Amiel Meiseles +5
Model agnostic feature attribution algorithms (such as SHAP and LIME) are ubiquitous techniques for explaining the decisions of complex classification models, such as deep neural n…
Attacking Object Detector Using A Universal Targeted Label-Switch Patch
Avishag Shapira, Ron Bitton, Dan Avraham +3
Adversarial attacks against deep learning-based object detectors (ODs) have been studied extensively in the past few years. These attacks cause the model to make incorrect predicti…
Improving Interpretability via Regularization of Neural Activation Sensitivity
Ofir Moshe, Gil Fidel, Ron Bitton +1
State-of-the-art deep neural networks (DNNs) are highly effective at tackling many real-world tasks. However, their wide adoption in mission-critical contexts is hampered by two ma…
BENN: Bias Estimation Using Deep Neural Network
Amit Giloni, Edita Grolman, Tanja Hagemann +4
The need to detect bias in machine learning (ML) models has led to the development of multiple bias detection methods, yet utilizing them is challenging since each method: i) explo…
Not All Datasets Are Born Equal: On Heterogeneous Data and Adversarial Examples
Yael Mathov, Eden Levy, Ziv Katzir +2
Recent work on adversarial learning has focused mainly on neural networks and domains where those networks excel, such as computer vision, or audio processing. The data in these do…
Adversarial robustness via stochastic regularization of neural activation sensitivity
Gil Fidel, Ron Bitton, Ziv Katzir +1
Recent works have shown that the input domain of any machine learning classifier is bound to contain adversarial examples. Thus we can no longer hope to immune classifiers against…
FOOD: Fast Out-Of-Distribution Detector
Guy Amit, Moshe Levy, Ishai Rosenberg +2
Deep neural networks (DNNs) perform well at classifying inputs associated with the classes they have been trained on, which are known as in distribution inputs. However, out-of-dis…
Hierarchical Deep Reinforcement Learning Approach for Multi-Objective Scheduling With Varying Queue Sizes
Yoni Birman, Ziv Ido, Gilad Katz +1
Multi-objective task scheduling (MOTS) is the task scheduling while optimizing multiple and possibly contradicting constraints. A challenging extension of this problem occurs when…
Adversarial Machine Learning Attacks and Defense Methods in the Cyber Security Domain
Ihai Rosenberg, Asaf Shabtai, Yuval Elovici +1
In recent years machine learning algorithms, and more specifically deep learning algorithms, have been widely used in many fields, including cyber security. However, machine learni…
GIM: Gaussian Isolation Machines
Guy Amit, Ishai Rosenberg, Moshe Levy +3
In many cases, neural network classifiers are likely to be exposed to input data that is outside of their training distribution data. Samples from outside the distribution may be c…
Can't Boil This Frog: Robustness of Online-Trained Autoencoder-Based Anomaly Detectors to Adversarial Poisoning Attacks
Moshe Kravchik, Asaf Shabtai
In recent years, a variety of effective neural network-based methods for anomaly and cyber attack detection in industrial control systems (ICSs) have been demonstrated in the liter…
When Explainability Meets Adversarial Learning: Detecting Adversarial Examples using SHAP Signatures
Gil Fidel, Ron Bitton, Asaf Shabtai
State-of-the-art deep neural networks (DNNs) are highly effective in solving many complex real-world problems. However, these models are vulnerable to adversarial perturbation atta…
MDGAN: Boosting Anomaly Detection Using \\Multi-Discriminator Generative Adversarial Networks
Yotam Intrator, Gilad Katz, Asaf Shabtai
Anomaly detection is often considered a challenging field of machine learning due to the difficulty of obtaining anomalous samples for training and the need to obtain a sufficient…
Classification of Smartphone Users Using Internet Traffic
Andrey Finkelstein, Ron Biton, Rami Puzis +1
Today, smartphone devices are owned by a large portion of the population and have become a very popular platform for accessing the Internet. Smartphones provide the user with immed…
Anomaly Detection Using the Knowledge-based Temporal Abstraction Method
Asaf Shabtai
The rapid growth in stored time-oriented data necessitates the development of new methods for handling, processing, and interpreting large amounts of temporal data. One important e…