Related papers: BinaryShield: Cross-Service Threat Intelligence in…
With the increasing use of conversational AI systems, there is growing concern over privacy leaks, especially when users share sensitive personal data in interactions with Large Language Models (LLMs). Conversations shared with these models…
With the increasing emphasis on privacy regulations, such as GDPR, protecting individual privacy and ensuring compliance have become critical concerns for both individuals and organizations. Privacy-preserving machine learning (PPML) is an…
Large Language Models (LLMs) like GPT-4, LLaMA, and Qwen have demonstrated remarkable success across a wide range of applications. However, these models remain inherently vulnerable to prompt injection attacks, which can bypass existing…
Large language models (LLMs) are increasingly deployed as the service backend for LLM-integrated applications such as code completion and AI-powered search. LLM-integrated applications serve as middleware to refine users' queries with…
Current research in adversarial robustness of LLMs focuses on discrete input manipulations in the natural language space, which can be directly transferred to closed-source models. However, this approach neglects the steady progression of…
As language models (LMs) are widely utilized in personalized communication scenarios (e.g., sending emails, writing social media posts) and endowed with a certain level of agency, ensuring they act in accordance with the contextual privacy…
Large Vision-Language Models (LVLMs) unlock powerful multimodal reasoning but also expand the attack surface, particularly through adversarial inputs that conceal harmful goals in benign prompts. We propose SHIELD, a lightweight,…
Binary analysis plays a pivotal role in security domains such as malware detection and vulnerability discovery, yet it remains labor-intensive and heavily reliant on expert knowledge. General-purpose large language models (LLMs) perform…
When applying machine learning to sensitive data, one has to find a balance between accuracy, information security, and computational-complexity. Recent studies combined Homomorphic Encryption with neural networks to make inferences while…
Large language models (LLMs) are increasingly deployed in real-world applications, raising concerns about their security. While jailbreak attacks highlight failures under overtly harmful queries, they overlook a critical risk: incorrectly…
Cryptographic algorithm implementations are vulnerable to Cold Boot attacks, which consist in exploiting the persistence of RAM cells across reboots or power down cycles to read the memory contents and recover precious sensitive data. The…
Despite the general capabilities of Large Language Models (LLM), these models still request fine-tuning or adaptation with customized data when meeting specific business demands. However, this process inevitably introduces new threats,…
Secure information retrieval is an essential task in today's highly digitised society. In some applications, it may be necessary that user query's privacy and database content's security are enforced. For these settings, symmetric private…
As LLMs continue to increase in parameter size, the computational resources required to run them are available to fewer parties. Therefore, third-party inference services -- where LLMs are hosted by third parties with significant…
Large language models (LLMs) are increasingly deployed in high-stakes domains, yet a unified treatment of their overlapping safety challenges remains lacking. We present SafeLM, a framework that jointly addresses four pillars of LLM safety:…
In recent years, insider threats and attacks have been increasing in terms of frequency and cost to the corporate business. The utilization of end-to-end encrypted instant messaging applications (WhatsApp, Telegram, VPN) by malicious…
The discourse on privacy risks in Large Language Models (LLMs) has disproportionately focused on verbatim memorization of training data, while a constellation of more immediate and scalable privacy threats remain underexplored. This…
Graph Prompt Learning (GPL) represents an innovative approach in graph representation learning, enabling task-specific adaptations by fine-tuning prompts without altering the underlying pre-trained model. Despite its growing prominence, the…
Federated Learning (FL) has recently emerged as a revolutionary approach to collaborative training Machine Learning models. In particular, it enables decentralized model training while preserving data privacy, but its distributed nature…
Insider threat detection (ITD) requires analyzing sparse, heterogeneous user behavior. Existing ITD methods predominantly rely on single-view modeling, resulting in limited coverage and missed anomalies. While multi-view learning has shown…