5 papers · 1 filter
Forecasting Cybersecurity Incidents Using Geopolitical Data and Large Language Models
Mark Fesenko, Abdullah Garra, Yaniv Harel +1
Predicting security incidents is a profound task critical for informing proactive defensive measures and cyber-insurance policies. Prior work tackling this problem mainly utilized…
The TellTail of Embeddings: Fingerprinting Retrievers in Black-Box Systems
Abdullah Garra, Matan Ben-Tov, Mahmood Sharif
Dense embedding models are core to modern text retrieval, enabling systems ranging from web search to retrieval-augmented generation (RAG). Yet, retrievers are usually deployed wit…
Universal Jailbreak Suffixes Are Strong Attention Hijackers
Matan Ben-Tov, Mor Geva, Mahmood Sharif
We study suffix-based jailbreaks$\unicode{x2013}$a powerful family of attacks against large language models (LLMs) that optimize adversarial suffixes to circumvent safety alignment…
CaFA: Cost-aware, Feasible Attacks With Database Constraints Against Neural Tabular Classifiers
Matan Ben-Tov, Daniel Deutch, Nave Frost +1
This work presents CaFA, a system for Cost-aware Feasible Attacks for assessing the robustness of neural tabular classifiers against adversarial examples realizable in the problem…
GASLITEing the Retrieval: Exploring Vulnerabilities in Dense Embedding-based Search
Matan Ben-Tov, Mahmood Sharif
Dense embedding-based text retrieval$\unicode{x2013}$retrieval of relevant passages from corpora via deep learning encodings$\unicode{x2013}$has emerged as a powerful method attain…