Related papers: Revisiting Main Memory-Based Covert and Side Chann…
Neural networks (NNs) are growing in importance and complexity. A neural network's performance (and energy efficiency) can be bound either by computation or memory resources. The processing-in-memory (PIM) paradigm, where computation is…
Microarchitectural timing attacks exploit subtle timing variations caused by hardware behaviors to leak sensitive information. In this paper, we introduce MCHammer, a novel side-channel technique that leverages machine clears induced by…
Edge deployment of low-batch large language models (LLMs) faces critical memory bandwidth bottlenecks when executing memory-intensive general matrix-vector multiplications (GEMV) operations. While digital processing-in-memory (PIM)…
The widespread adoption of Large Language Models (LLMs) has exponentially increased the demand for efficient serving systems. With growing requests and context lengths, key-value (KV)-related operations, including attention computation and…
As data-intensive applications increasingly strain conventional computing systems, processing-in-memory (PIM) has emerged as a promising paradigm to alleviate the memory wall by minimizing data transfer between memory and processing units.…
Prompt-based approaches offer a cutting-edge solution to data privacy issues in continual learning, particularly in scenarios involving multiple data suppliers where long-term storage of private user data is prohibited. Despite delivering…
In-DRAM Processing-In-Memory (DRAM-PIM) has emerged as a promising approach to accelerate memory-intensive workloads by mitigating data transfer overhead between DRAM and the host processor. Bit-serial DRAM-PIM architectures, further…
Processing-In-Memory (PIM) is a novel approach that augments existing DRAM memory chips with lightweight logic. By allowing to offload computations to the PIM system, this architecture allows for circumventing the data-bottleneck problem…
Our ISCA 2015 paper provides a new programmable processing-in-memory (PIM) architecture and system design that can accelerate key data-intensive applications, with a focus on graph processing workloads. Our major idea was to completely…
Traditional side-channels take advantage of secrets being used as inputs to unsafe instructions, used for memory accesses, or used in control flow decisions. Constant-time programming, which restricts such code patterns, has been widely…
Analog compute-in-memory (CIM) in static random-access memory (SRAM) is promising for accelerating deep learning inference by circumventing the memory wall and exploiting ultra-efficient analog low-precision arithmetic. Latest analog CIM…
Our goal in this dissertation is to provide tools, programming models, and system support for PIM architectures (with a focus on DRAM-based solutions), to ease the adoption of PIM in current and future systems. To this end, we make at least…
Language models (LMs) may memorize personally identifiable information (PII) from training data, enabling adversaries to extract it during inference. Existing defense mechanisms such as differential privacy (DP) reduce this leakage, but…
In modern computer architectures, the performance of many memory-bound workloads (e.g., machine learning, graph processing, databases) is limited by the data movement bottleneck that emerges when transferring large amounts of data between…
Processing-in-memory (PIM), an increasingly studied neuromorphic hardware, promises orders of energy and throughput improvements for deep learning inference. Leveraging the massively parallel and efficient analog computing inside memories,…
Privacy leakage in LLM agents is often studied through individual storage or execution components, such as memory modules, retrieval pipelines, or tool-mediated artifacts. However, these settings are typically analyzed in isolation, making…
Modern processors are highly optimized systems where every single cycle of computation time matters. Many optimizations depend on the data that is being processed. Software-based microarchitectural attacks exploit effects of these…
DRAM-based main memory and its associated components increasingly account for a significant portion of application performance bottlenecks and power budget demands inside the computing ecosystem. To alleviate the problems of storage density…
Cyberattacks targeting critical infrastructures, such as water treatment facilities, represent significant threats to public health, safety, and the environment. This paper introduces a systematic approach for modeling and assessing covert…
Modern processors use branch prediction and speculative execution to maximize performance. For example, if the destination of a branch depends on a memory value that is in the process of being read, CPUs will try guess the destination and…