16 citations · 34 across the 13 of their papers we have counts for
10 papers · 1 filter
RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents
Mohamed Dhouib, Clement Elliker, Alexi Canesse +6
Tool-using language-model agents are vulnerable to indirect prompt injection because they must act on untrusted external content. Existing training-time defenses can reduce attack…
ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?
Zhun Wang, Nico Schiller, Hongwei Li +13
AI agents are rapidly gaining capabilities that could significantly reshape cybersecurity, making rigorous evaluation urgent. A critical capability is exploitation: turning a vulne…
Profiling Resilient to Change in Probe Position
Elie Bursztein, Michael Gruber, Karel Král +3
Side Channel Analysis (SCA) relaxes the black-box assumption of conventional cryptanalysis by incorporating physical measurements acquired during cryptographic operations. Electro-…
DROIDCCT: Cryptographic Compliance Test via Trillion-Scale Measurement
Daniel Moghimi, Alexandru-Cosmin Mihai, Borbala Benko +6
We develop DroidCCT, a distributed test framework to evaluate the scale of a wide range of failures/bugs in cryptography for end users. DroidCCT relies on passive analysis of artif…
Evaluating the Robustness of a Production Malware Detection System to Transferable Adversarial Attacks
Milad Nasr, Yanick Fratantonio, Luca Invernizzi +7
As deep learning models become widely deployed as components within larger production systems, their individual shortcomings can create system-level vulnerabilities with real-world…
Facade: High-Precision Insider Threat Detection Using Deep Contextual Anomaly Detection
Alex Kantchelian, Casper Neo, Ryan Stevens +10
Insiders with privileged access have the power to cause great harm to their organization. Even a single insider threat incident can be catastrophic, resulting in both financial los…
Magika: AI-Powered Content-Type Detection
Yanick Fratantonio, Luca Invernizzi, Loua Farah +9
The task of content-type detection -- which entails identifying the data encoded in an arbitrary byte sequence -- is critical for operating systems, development, reverse engineerin…
Supporting Human Raters with the Detection of Harmful Content using Large Language Models
Kurt Thomas, Patrick Gage Kelley, David Tao +7
In this paper, we explore the feasibility of leveraging large language models (LLMs) to automate or otherwise assist human raters with identifying harmful content including hate sp…
Generalized Power Attacks against Crypto Hardware using Long-Range Deep Learning
Elie Bursztein, Luca Invernizzi, Karel Král +3
To make cryptographic processors more resilient against side-channel attacks, engineers have developed various countermeasures. However, the effectiveness of these countermeasures…
CoinPolice:Detecting Hidden Cryptojacking Attacks with Neural Networks
Ivan Petrov, Luca Invernizzi, Elie Bursztein
Traffic monetization is a crucial component of running most for-profit online businesses. One of its latest incarnations is cryptocurrency mining, where a website instructs the vis…