Related papers: PoisonCap: Efficient Hierarchical Temporal Safety …
The safety of mental health AI is often judged at the wrong temporal scale. Current evaluations typically score isolated responses, endpoint outcomes, or aggregate dialogue quality, while clinically consequential failures may arise from the…
In scientific computing and data science disciplines, it is often necessary to share application workflows and repeat results. Current tools containerize application workflows, and share the resulting container for repeating results. These…
Memory safety in complex applications implemented in unsafe programming languages such as C/C++ is still an unresolved problem in practice. Many different types of defenses have been proposed in the past to mitigate this problem. The most…
Micro-architectural attacks use information leaked through shared resources to break hardware-enforced isolation. These attacks have been used to steal private information ranging from cryptographic keys to privileged Operating System (OS)…
We extend the Faulty RAM model by Finocchi and Italiano (2008) by adding a safe memory of arbitrary size $S$, and we then derive tradeoffs between the performance of resilient algorithmic techniques and the size of the safe memory. Let…
Fault-tolerant distributed applications require mechanisms to recover data lost via a process failure. On modern cluster systems it is typically impractical to request replacement resources after such a failure. Therefore, applications have…
In order to protect devices from physical manipulations, protective security enclosures were developed. However, these battery-backed solutions come with a reduced lifetime, and have to be actively and continuously monitored. In order to…
Pipeline parallelism (PP) is widely used for training large language models (LLMs), yet its scalability is often constrained by high activation memory consumption as the number of in-flight microbatches grows with the degree of PP. In this…
Continual Learning (CL) is an emerging machine learning paradigm that aims to learn from a continuous stream of tasks without forgetting knowledge learned from the previous tasks. To avoid performance decrease caused by forgetting, prior…
Computational storage, known as a solution to significantly reduce the latency by moving data-processing down to the data storage, has received wide attention because of its potential to accelerate data-driven devices at the edge. To meet…
Current reconfiguration techniques are based on starting the system in a consistent configuration, in which all participating entities are in their initial state. Starting from that state, the system must preserve consistency as long as a…
The efficacy of address space layout randomization has been formally demonstrated in a shared-memory model by Abadi et al., contingent on specific assumptions about victim programs. However, modern operating systems, implementing layout…
Ransomware poses a significant threat to individuals and organisations, compelling tools to investigate its behaviour and the effectiveness of mitigations. To answer this need, we present SAFARI, an open-source framework designed for safe…
Many cache designs have been proposed to guard against contention-based side-channel attacks. One well-known type of cache is the randomized remapping cache. Many randomized remapping caches provide fixed or over protection, which leads to…
Large language model agents equipped with persistent memory are vulnerable to memory poisoning attacks, where adversaries inject malicious instructions through query only interactions that corrupt the agents long term memory and influence…
Ransomware core capability, unauthorized encryption, demands controls that identify and block malicious cryptographic activity without disrupting legitimate use. We present a probabilistic, risk-based access control architecture that…
PHOENIXOS (PHOS) is the first OS service that can concurrently checkpoint and restore (C/R) GPU processes--a fundamental capability for critical tasks such as fault tolerance, process migration, and fast startup. While concurrent C/R is…
The adversarial model presented by trusted execution environments (TEEs) has prompted researchers to investigate unusual attack vectors. One particularly powerful class of controlled-channel attacks abuses page-table modifications to…
Hierarchical Temporal Memory is a new machine learning algorithm intended to mimic the working principle of neocortex, part of the human brain, which is responsible for learning, classification, and making predictions. Although many works…
This paper presents a prepare-and-measure scheme using $N$-dimensional quantum particles as information carriers where $N$ is a prime power. One of the key ingredients used to resist eavesdropping in this scheme is to depolarize all Pauli…