1.5k citations · 2.3k across the 133 of their papers we have counts for
14 papers · 1 filter
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…
DIESEL -- Dynamic Inference-Guidance via Evasion of Semantic Embeddings in LLMs
Ben Ganon, Alon Zolfi, Omer Hofman +4
In recent years, large language models (LLMs) have had great success in tasks such as casual conversation, contributing to significant advancements in domains like virtual assistan…
LISAA: A Framework for Large Language Model Information Security Awareness Assessment
Ofir Cohen, Gil Ari Agmon, Asaf Shabtai +1
The popularity of large language models (LLMs) continues to grow, and LLM-based assistants have become ubiquitous. Information security awareness (ISA) is an important yet underexp…
Detection of Compromised Functions in a Serverless Cloud Environment
Danielle Lavi, Oleg Brodt, Dudu Mimran +2
Serverless computing is an emerging cloud paradigm with serverless functions at its core. While serverless environments enable software developers to focus on developing applicatio…
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…
LLMCloudHunter: Harnessing LLMs for Automated Extraction of Detection Rules from Cloud-Based CTI
Yuval Schwartz, Lavi Benshimol, Dudu Mimran +2
As the number and sophistication of cyber attacks have increased, threat hunting has become a critical aspect of active security, enabling proactive detection and mitigation of thr…
GeNet: A Multimodal LLM-Based Co-Pilot for Network Topology and Configuration
Beni Ifland, Elad Duani, Rubin Krief +9
Communication network engineering in enterprise environments is traditionally a complex, time-consuming, and error-prone manual process. Most research on network engineering automa…
RAPID: Robust APT Detection and Investigation Using Context-Aware Deep Learning
Yonatan Amaru, Prasanna Wudali, Yuval Elovici +1
Advanced persistent threats (APTs) pose significant challenges for organizations, leading to data breaches, financial losses, and reputational damage. Existing provenance-based app…
GenKubeSec: LLM-Based Kubernetes Misconfiguration Detection, Localization, Reasoning, and Remediation
Ehud Malul, Yair Meidan, Dudu Mimran +2
A key challenge associated with Kubernetes configuration files (KCFs) is that they are often highly complex and error-prone, leading to security vulnerabilities and operational set…
Observability and Incident Response in Managed Serverless Environments Using Ontology-Based Log Monitoring
Lavi Ben-Shimol, Edita Grolman, Aviad Elyashar +7
In a fully managed serverless environment, the cloud service provider is responsible for securing the cloud infrastructure, thereby reducing the operational and maintenance efforts…
CodeCloak: A Method for Evaluating and Mitigating Code Leakage by LLM Code Assistants
Amit Finkman Noah, Avishag Shapira, Eden Bar Kochva +4
LLM-based code assistants are becoming increasingly popular among developers. These tools help developers improve their coding efficiency and reduce errors by providing real-time s…
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…
DeSparsify: Adversarial Attack Against Token Sparsification Mechanisms in Vision Transformers
Oryan Yehezkel, Alon Zolfi, Amit Baras +2
Vision transformers have contributed greatly to advancements in the computer vision domain, demonstrating state-of-the-art performance in diverse tasks (e.g., image classification,…
GPT in Sheep's Clothing: The Risk of Customized GPTs
Sagiv Antebi, Noam Azulay, Edan Habler +3
In November 2023, OpenAI introduced a new service allowing users to create custom versions of ChatGPT (GPTs) by using specific instructions and knowledge to guide the model's behav…