Related papers: A Last-Level Defense for Application Integrity and…

With the rapidly evolving next-generation systems-of-systems, we face new security, resilience, and operational assurance challenges. In the face of the increasing attack landscape, it is necessary to cater to efficient mechanisms to verify…

Unauthorized data alteration has been a longstanding threat since the emergence of malware. System and application software can be reinstalled and hardware can be replaced, but user data is priceless in many cases. Especially in recent…

A TrustZone TEE often invokes an external filesystem. While filedata can be encrypted, the revealed file activities can leak secrets. To hide the file activities from the filesystem and its OS, we propose Enigma, a deception-based defense…

CaMeL (Capabilities for Machine Learning) introduces a capability-based sandbox to mitigate prompt injection attacks in large language model (LLM) agents. While effective, CaMeL assumes a trusted user prompt, omits side-channel concerns,…

Prompt injection attacks, where untrusted data contains an injected prompt to manipulate the system, have been listed as the top security threat to LLM-integrated applications. Model-level prompt injection defenses have shown strong…

Data theft and leakage, caused by external adversaries and insiders, demonstrate the need for protecting user data. Trusted Execution Environments (TEEs) offer a promising solution by creating secure environments that protect data and code…

The use of unsafe programming languages still remains one of the major root causes of software vulnerabilities. Although well-known defenses that detect and mitigate memory-safety related issues exist, they don't address the challenge of…

Applications running in Trusted Execution Environments (TEEs) commonly use untrusted external services such as host File System. Adversaries may maliciously alter the normal service behavior to trigger subtle application bugs that would…

Confidential Computing enhances privacy of data in-use through hardware-based Trusted Execution Environments (TEEs) that use attestation to verify their integrity, authenticity, and certain runtime properties, along with those of the…

Trusted Execution Environments (TEEs) have been proposed as a solution to protect code confidentiality in scenarios where computation is outsourced to an untrusted operator. We study the resilience of such solutions to side-channel attacks…

Federated Learning (FL) is a distributed machine learning approach that has emerged as an effective way to address recent privacy concerns. However, FL introduces the need for additional security measures as FL alone is still subject to…

Modern computer systems tend to rely on large trusted computing bases (TCBs) for operations. To address the TCB bloating problem, hardware vendors have developed mechanisms to enable or facilitate the creation of a trusted execution…

Trusted Execution Environments (TEEs), such as Intel Software Guard eXtensions (SGX), are considered as a promising approach to resolve security challenges in clouds. TEEs protect the confidentiality and integrity of application code and…

The majority of cloud providers offers users the possibility to deploy Trusted Execution Environments (TEEs) to protect their data and processes from high privileged adversaries. This offer is intended to address concerns of users when…

Large language models (LLMs) are increasingly applied in fields such as finance, education, and governance due to their ability to generate human-like text and adapt to specialized tasks. However, their widespread adoption raises critical…

Proprietary large language models (LLMs) have been widely applied in various scenarios. Additionally, deploying LLMs on edge devices is trending for efficiency and privacy reasons. However, edge deployment of proprietary LLMs introduces new…

Trusted Execution Environments (TEE) are used to safeguard on-device models. However, directly employing TEEs to secure the entire DNN model is challenging due to the limited computational speed. Utilizing GPU can accelerate DNN's…

LLM-integrated app systems extend the utility of Large Language Models (LLMs) with third-party apps that are invoked by a system LLM using interleaved planning and execution phases to answer user queries. These systems introduce new attack…

Large language models (LLMs) remain acutely vulnerable to prompt injection and related jailbreak attacks; heuristic guardrails (rules, filters, LLM judges) are routinely bypassed. We present Contextual Integrity Verification (CIV), an…

The distributed (federated) LLM is an important method for co-training the domain-specific LLM using siloed data. However, maliciously stealing model parameters and data from the server or client side has become an urgent problem to be…