Related papers: Semantic Intent Fragmentation: A Single-Shot Compo…

Multi-agent large language model (LLM) systems are rapidly emerging as the dominant architecture for enterprise AI automation, yet production deployments exhibit failure rates between 41% and 86.7%, with nearly 79% of failures originating…

Microarchitectural timing attacks are a type of information leakage attack, which exploit the time-shared microarchitectural components, such as caches, translation look-aside buffers (TLBs), branch prediction unit (BPU), and speculative…

Multi-agent orchestration frameworks such as LangChain, LangGraph, and CrewAI route tasks through graph-based pipelines but do not enforce the stage constraints that govern real business processes. We present SDOF, a framework that treats…

Large Language Models (LLMs) remain vulnerable to jailbreak attacks, where adversarially crafted prompts induce policy-violating responses despite safety alignment. Existing defenses typically improve safety through external filtering,…

With the development of artificial intelligence (AI), Agentic AI (AAI) based on large language models (LLMs) is gradually being applied to network management. However, in edge network environments, high user mobility and implicit service…

Speculative execution enhances processor performance by predicting intermediate results and executing instructions based on these predictions. However, incorrect predictions can lead to security vulnerabilities, as speculative instructions…

We introduce \emph{self-jailbreaking}, a threat model in which an aligned LLM guides its own compromise. Unlike most jailbreak techniques, which often rely on handcrafted prompts or separate attacker models, self-jailbreaking requires no…

The disaggregation of the Radio Access Network (RAN) introduces unprecedented flexibility but significant operational complexity, necessitating automated management frameworks. However, current Open RAN (O-RAN) orchestration relies on…

Multimodal Large Language Models (MLLMs) are increasingly deployed in stateless systems, such as autonomous driving and robotics. This paper investigates a novel threat: Semantic-Aware Hijacking. We explore the feasibility of hijacking…

Adversarial attacks hamper the decision-making ability of neural networks by perturbing the input signal. The addition of calculated small distortion to images, for instance, can deceive a well-trained image classification network. In this…

Intent-based networking aims to simplify network operation by translating operator intents into a collection of policies, configurations, and control actions. However, this translation process relies on heuristics and loose coupling. It…

Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an external environment; this makes them susceptible to prompt injections when dealing with untrusted data. To overcome this limitation, we propose…

The growing sophistication, frequency, and diversity of cyberattacks increasingly exceed the capacity of individual entities to fully understand and counter them. While existing solutions, such as Security Information and Event Management…

A major bottleneck in search-based program synthesis is the exponentially growing search space which makes learning large programs intractable. Humans mitigate this problem by leveraging the compositional nature of the real world: In…

Split Federated Learning (SFL) is an emerging paradigm for privacy-preserving distributed learning. However, it remains vulnerable to sophisticated data poisoning attacks targeting local features, labels, smashed data, and model weights.…

As Large Language Model (LLM) agents become more capable, their coordinated use in the form of multi-agent systems is anticipated to emerge as a practical paradigm. Prior work has examined the safety and misuse risks associated with agents.…

Recently, Large language models (LLMs) with powerful general capabilities have been increasingly integrated into various Web applications, while undergoing alignment training to ensure that the generated content aligns with user intent and…

We propose and study a planning problem we call Sequential Fault-Intolerant Process Planning (SFIPP). SFIPP captures a reward structure common in many sequential multi-stage decision problems where the planning is deemed successful only if…

The safety alignment of Large Language Models (LLMs) is vulnerable to both manual and automated jailbreak attacks, which adversarially trigger LLMs to output harmful content. However, current methods for jailbreaking LLMs, which nest entire…

Safety Instrumented Systems (SIS) protect major hazard facilities, e.g. power plants, against catastrophic accidents. An SIS consists of hardware components and a controller software -- the ``program''. Current safety analyses of SIS'…