Related papers: Selfie: User-defined Sensitive Memory Protection a…
Safety evaluations of memory-equipped LLM agents typically measure within-task safety: whether an agent completes a single scenario safely, often under adversarial conditions such as prompt injection or memory poisoning. In deployment,…
Unsafe Rust code is necessary for interoperability with C/C++ libraries and implementing low-level data structures, but it can cause memory safety violations in otherwise memory-safe Rust programs. Sanitizers can catch such memory errors at…
Effectively explaining decisions of black-box machine learning models is critical to responsible deployment of AI systems that rely on them. Recognizing their importance, the field of explainable AI (XAI) provides several techniques to…
We consider a living organism as an observer of the evolution of its environment recording sensory information about the state space X of the environment in real time. Sensory information is sampled and then processed on two levels. On the…
Memory consistency models define the order in which accesses to shared memory in a concurrent system may be observed to occur. Such models are a necessity since program order is not a reliable indicator of execution order, due to…
We consider a database $\vec{X} = (X_1,\cdots,X_n)$ containing the data of $n$ users. The data aggregator wants to publicise the database, but wishes to sanitise the dataset to hide sensitive data $S_i$ correlated to $X_i$. This setting is…
AI is increasingly used to enhance images and videos, both intentionally and unintentionally. As AI editing tools become more integrated into smartphones, users can modify or animate photos into realistic videos. This study examines the…
We describe SAFIUS, a secure accountable file system that resides over an untrusted storage. SAFIUS provides strong security guarantees like confidentiality, integrity, prevention from rollback attacks, and accountability. SAFIUS also…
Individuals lack oversight over systems that process their data. This can lead to discrimination and hidden biases that are hard to uncover. Recent data protection legislation tries to tackle these issues, but it is inadequate. It does not…
Neural networks pose a privacy risk due to their propensity to memorise and leak training data. We show that unique features occurring only once in training data are memorised by discriminative multi-layer perceptrons and convolutional…
Privacy protection in medical data is a legitimate obstacle for centralized machine learning applications. Here, we propose a client-server image segmentation system which allows for the analysis of multi-centric medical images while…
We introduce a new metric for measuring how well a model personalizes to a user's specific preferences. We define personalization as a weighting between performance on user specific data and performance on a more general global dataset that…
The rapid development of video surveillance systems for object detection, tracking, activity recognition, and anomaly detection has revolutionized our day-to-day lives while setting alarms for privacy concerns. It isn't easy to strike a…
The Self-Sovereign Identity (SSI) paradigm is instrumental for decentralised identity management, allowing an entity to create, manage, and present their digital credentials without relying on centralised authorities. Credential selective…
The ever-increasing adoption of Large Language Models in critical sectors like finance, healthcare, and government raises privacy concerns regarding the handling of sensitive Personally Identifiable Information (PII) during training. In…
Multiprocess systems, including grid systems, multiprocessors and multicore computers, incorporate a variety of specialized hardware and software mechanisms, which speed computation, but result in complex memory behavior. As a consequence,…
The fundamental trade-off between privacy and utility remains an active area of research. Our contribution is motivated by two observations. First, privacy mechanisms developed for one-time data release cannot straightforwardly be extended…
External fragmentation of physical memory occurs when adjacent differently sized regions of allocated physical memory are freed at different times, causing free memory to be physically discontiguous. It can significantly degrade system…
We present SuperLocalMemory, a local-first memory system for multi-agent AI that defends against OWASP ASI06 memory poisoning through architectural isolation and Bayesian trust scoring, while personalizing retrieval through adaptive…
This paper introduces the notion of a secure data capsule, which refers to an encapsulation of sensitive user information (such as a credit card number) along with code that implements an interface suitable for the use of such information…