Related papers: When malloc() Never Returns NULL -- Reliability as…
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…
Address Space Layout Randomization (ASLR) is one of the most prominently deployed mitigations against memory corruption attacks. ASLR randomly shuffles program virtual addresses to prevent attackers from knowing the location of program…
In recent years, high availability and reliability of Data Storage Systems (DSS) have been significantly threatened by soft errors occurring in storage controllers. Due to their specific functionality and hardware-software stack, error…
Android apps must work correctly even if their execution is interrupted by external events. For instance, an app must work properly even if a phone call is received, or after its layout is redrawn because the smartphone has been rotated.…
Improvements in main memory storage density are primarily driven by process technology scaling, which negatively impacts reliability by exacerbating various circuit-level error mechanisms. To compensate for growing error rates, both memory…
The importance of preventing microarchitectural timing side channels in security-critical applications has surged in recent years. Constant-time programming has emerged as a best-practice technique for preventing the leakage of secret…
Memory forensics is a powerful technique commonly adopted to investigate compromised machines and to detect stealthy computer attacks that do not store data on non-volatile storage. To employ this technique effectively, the analyst has to…
This paper describes LeftoverLocals: a vulnerability that allows data recovery from GPU memory created by another process on Apple, Qualcomm, and AMD GPUs. LeftoverLocals impacts the security posture of GPU applications, with particular…
Software-based memory-erasure protocols are two-party communication protocols where a verifier instructs a computational device to erase its memory and send a proof of erasure. They aim at guaranteeing that low-cost IoT devices are free of…
Persistent Memory (PM) makes possible recoverable applications that can preserve application progress across system reboots and power failures. Actual recoverability requires careful ordering of cacheline flushes, currently done in two…
Memory safety bugs, such as out-of-bound accesses (OOB) in GPU programs, can compromise the security and reliability of GPU-accelerated software. We report the existence of input-dependent OOBs in the wild that manifest only under specific…
Ownership is the concept of tracking aliases and mutations to data, useful for both memory safety and system design. The Rust programming language implements ownership via the borrow checker, a static analyzer that extends the core type…
Computer use agents are LLM-based agents that can directly interact with a graphical user interface, by processing screenshots or accessibility trees. While these systems are gaining popularity, their safety has been largely overlooked,…
By considering an unreliable oracle in a query-based model of quantum learning, we present a tradeoff relation between the oracle's reliability and the reusability of quantum state of the input data. The tradeoff relation manifests as the…
Security-critical tasks require proper isolation from untrusted software. Chip manufacturers design and include trusted execution environments (TEEs) in their processors to secure these tasks. The integrity and security of the software in…
Out-of-distribution (OOD) detection is essential for reliable and trustworthy machine learning. Recent multi-modal OOD detection leverages textual information from in-distribution (ID) class names for visual OOD detection, yet it currently…
A promising avenue for improving the effectiveness of behavioral-based malware detectors would be to combine fast traditional machine learning detectors with high-accuracy, but time-consuming deep learning models. The main idea would be to…
Ensuring the reliability and safety of machine learning models in open-world deployment is a central challenge in AI safety. This thesis develops both algorithmic and theoretical foundations to address key reliability issues arising from…
Machine unlearning (MU) seeks to eliminate the influence of specific training examples from deployed models. As large language models (LLMs) become widely used, managing risks arising from insufficient forgetting or utility loss is…
Online Reinforcement Learning (RL) offers a promising paradigm for enhancing GUI agents through direct environment interaction. However, its effectiveness is severely hindered by inefficient credit assignment in long-horizon tasks and…