Related papers: ShadowBound: Efficient Heap Memory Protection Thro…
Memory safety is an essential correctness property of software systems. For programs operating on linked heap-allocated data structures, the problem of proving memory safety boils down to analyzing the possible shapes of data structures,…
We give a rigorous characterization of what it means for a programming language to be memory safe, capturing the intuition that memory safety supports local reasoning about state. We formalize this principle in two ways. First, we show how…
Man-At-The-End (MATE) attackers are almighty adversaries against whom there exists no silver-bullet countermeasure. To raise the bar, a wide range of protection measures were proposed in the literature each of which adds resilience against…
Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into multiple categories: human-based, optimization-based, generation-based, and the…
Proprietary large language models (LLMs) exhibit strong generalization capabilities across diverse tasks and are increasingly deployed on edge devices for efficiency and privacy reasons. However, deploying proprietary LLMs at the edge…
High-Bandwidth Memory (HBM) delivers exceptional bandwidth and energy efficiency for AI workloads, but its high cost per bit, driven in part by stringent on-die reliability requirements, poses a growing barrier to scalable deployment. This…
Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone…
In the existing software development ecosystem, security issues introduced by third-party code cannot be overlooked. Among these security concerns, memory access vulnerabilities stand out prominently, leading to risks such as the theft or…
Widespread use of memory unsafe programming languages (e.g., C and C++) leaves many systems vulnerable to memory corruption attacks. A variety of defenses have been proposed to mitigate attacks that exploit memory errors to hijack the…
Confidential Computing (CC) has received increasing attention in recent years as a mechanism to protect user data from untrusted operating systems (OSes). Existing CC solutions hide confidential memory from the OS and/or encrypt it to…
As large language model (LLM)-powered agents are increasingly deployed to perform complex, real-world tasks, they face a growing class of attacks that exploit extended user-agent-environment interactions to pursue malicious objectives…
Rowhammer is a hardware security vulnerability at the heart of every system with modern DRAM-based memory. Despite its discovery a decade ago, comprehensive defenses remain elusive, while the probability of successful attacks grows with…
In this dissertation, we propose a memory and computing coordinated methodology to thoroughly exploit the characteristics and capabilities of the GPU-based heterogeneous system to effectively optimize applications' performance and privacy.…
Stack-based memory corruption vulnerabilities have long been exploited by attackers to execute arbitrary code or perform unauthorized memory operations. Various defense mechanisms have been introduced to mitigate stack memory errors, but…
The eBPF framework enables execution of user-provided code in the Linux kernel. In the last few years, a large ecosystem of cloud services has leveraged eBPF to enhance container security, system observability, and network management.…
Memory safety errors continue to pose a significant threat to current computing systems, and graphics processing units (GPUs) are no exception. A prominent class of memory safety algorithms is allocation-based solutions. The key idea is to…
Temporal memory corruptions are commonly exploited software vulnerabilities that can lead to powerful attacks. Despite significant progress made by decades of research on mitigation techniques, existing countermeasures fall short due to…
Large Language Models (LLMs) have evolved into AI agents that interact with external tools and environments to perform complex tasks. The Model Context Protocol (MCP) has become the de facto standard for connecting agents with such…
Honeypots are designed to trap the attacker with the purpose of investigating its malicious behavior. Owing to the increasing variety and sophistication of cyber attacks, how to capture high-quality attack data has become a challenge in the…
Large Language Model (LLM) agents use memory to learn from past interactions, enabling autonomous planning and decision-making in complex environments. However, this reliance on memory introduces a critical security risk: an adversary can…