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

Host-based intrusion detection system (HIDS) is a key defense component to protect the organizations from advanced threats like Advanced Persistent Threats (APT). By analyzing the fine-grained logs with approaches like data provenance, HIDS…

The rapid advancement of Large Language Models (LLMs) has driven significant progress in Natural Language Interface to Database (NLIDB). However, the widespread adoption of LLMs has raised critical privacy and security concerns. During…

The growth of low-end hardware has led to a proliferation of machine learning-based services in edge applications. These applications gather contextual information about users and provide some services, such as personalized offers, through…

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…

Advances in machine learning (ML) in recent years have enabled a dizzying array of applications such as data analytics, autonomous systems, and security diagnostics. ML is now pervasive---new systems and models are being deployed in every…

The blockchain-based smart contract lacks privacy since the contract state and instruction code are exposed to the public. Combining smart-contract execution with Trusted Execution Environments (TEEs) provides an efficient solution, called…

Large Language Models (LLMs) have become increasingly vulnerable to jailbreak attacks that circumvent their safety mechanisms. While existing defense methods either suffer from adaptive attacks or require computationally expensive auxiliary…

Autonomous and robotic systems are increasingly being trusted with sensitive activities with potentially serious consequences if that trust is broken. Runtime verification techniques present a natural source of inspiration for monitoring…

LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hundreds of rounds and tested it against nine defense…

The rise of Large Language Models has created a general excitement about the great potential for a myriad of applications. While LLMs offer many possibilities, questions about safety, privacy, and ethics have emerged, and all the key actors…

Protection of Web applications is an activity that requires constant monitoring of security threats as well as looking for solutions in this field. Since protection has moved from the lower layers of OSI models to the application layer and…

We present a practical framework to deploy privacy-preserving machine learning (PPML) applications in untrusted clouds based on a trusted execution environment (TEE). Specifically, we shield unmodified PyTorch ML applications by running…

Modern single page web applications require client-side executions of application logic, including critical functionality such as client-side cryptography. Existing mechanisms such as TLS and Subresource Integrity secure the communication…

Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…

Adversarial attack breaks the boundaries of traditional security defense. For adversarial attack and the characteristics of cloud services, we propose Security Development Lifecycle for Machine Learning applications, e.g., SDL for ML. The…

Large language models (LLMs) are widely used for task understanding and action planning in embodied intelligence (EI) systems, but their adoption substantially increases vulnerability to jailbreak attacks. While recent work explores…

Retrieval-Augmented Generation (RAG) and Supervised Finetuning (SFT) have become the predominant paradigms for equipping Large Language Models (LLMs) with external knowledge for diverse, knowledge-intensive tasks. However, while such…

Hardware support for trusted execution in modern CPUs enables tenants to shield their data processing workloads in otherwise untrusted cloud environments. Runtime systems for the trusted execution must rely on an interface to the untrusted…

Attestation means providing evidence that a remote target system is worthy of trust for some sensitive interaction. Although attestation is already used in network access control, security management, and trusted execution environments, it…

The big data industry is facing new challenges as concerns about privacy leakage soar. One of the remedies to privacy breach incidents is to encapsulate computations over sensitive data within hardware-assisted Trusted Execution…