Related papers: ShadowBound: Efficient Heap Memory Protection Thro…
Deploying large language models (LLMs) as autonomous browser agents exposes a significant attack surface in the form of Indirect Prompt Injection (IPI). Cloud-based defenses can provide strong semantic analysis, but they introduce latency…
Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect prompt injection. Adversaries exploit this weakness by…
Large Language Model based multi-agent systems are revolutionizing autonomous communication and collaboration, yet they remain vulnerable to security threats like unauthorized access and data breaches. To address this, we introduce…
Modern shared memory multiprocessors permit reordering of memory operations for performance reasons. These reorderings are often a source of subtle bugs in programs written for such architectures. Traditional approaches to verify weak…
Backdoor attacks are dangerous and difficult to prevent in federated learning (FL), where training data is sourced from untrusted clients over long periods of time. These difficulties arise because: (a) defenders in FL do not have access to…
Intra-session network coding is known to be vulnerable to pollution attacks. In this work, first, we introduce a novel homomorphic MAC scheme called SpaceMac, which allows an intermediate node to verify if its received packets belong to a…
The rapid evolution of cloud computing technologies and the increasing number of cloud applications have provided numerous benefits in our daily lives. However, the diversity and complexity of different components pose a significant…
Cyber-Physical Systems (CPS) are being widely adopted in critical infrastructures, such as smart grids, nuclear plants, water systems, transportation systems, manufacturing and healthcare services, among others. However, the increasing…
This paper introduces a novel approach for the automated selection of software protections to mitigate MATE risks against critical assets within software applications. We formalize the key elements involved in protection decision-making -…
Software transactional memory implementations which allow transactions to work on inconsistent states of shared data, risk to cause application visible errors such as memory access violations or endless loops. Hence, many implementations…
System prompts are critical for guiding the behavior of Large Language Models (LLMs), yet they often contain proprietary logic or sensitive information, making them a prime target for extraction attacks. Adversarial queries can successfully…
Byte-addressable, non-volatile memory (NVM) is emerging as a promising technology. To facilitate its wide adoption, employing NVM in managed runtimes like JVM has proven to be an effective approach (i.e., managed NVM). However, such an…
The deployment of large-scale distributed systems, e.g., publish-subscribe platforms, that operate over sensitive data using the infrastructure of public cloud providers, is nowadays heavily hindered by the surging lack of trust toward the…
Existing language model safety evaluations focus on overt attacks and low-stakes tasks. In reality, an attacker can easily subvert existing safeguards by requesting help on small, benign-seeming tasks across many independent queries.…
Memory-related errors remain an important cause of software vulnerabilities. While mitigation techniques such as using memory-safe languages are promising solutions, these do not address software resilience and availability. In this paper,…
The widespread use of publicly available pre-trained encoders from self-supervised learning (SSL) has exposed a critical vulnerability: their susceptibility to downstream-agnostic adversarial examples (DAEs), which are crafted without…
The use of unsafe programming languages still remains one of the major root causes of software vulnerabilities. Although well-known defenses that detect and mitigate memory-safety related issues exist, they don't address the challenge of…
Learning-based quadruped controllers achieve impressive agility but typically lack formal safety guarantees under model uncertainty, perception noise, and unstructured contact conditions. We introduce SafeMind, a differentiable stochastic…
The increasing prevalence of adversarial attacks on Artificial Intelligence (AI) systems has created a need for innovative security measures. However, the current methods of defending against these attacks often come with a high computing…
Memory latency, bandwidth, capacity, and energy increasingly limit performance. In this paper, we reconsider proposed system architectures that consist of huge (many-terabyte to petabyte scale) memories shared among large numbers of CPUs.…