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

Fragmentation is a routine part of communication in 6LoWPAN-based IoT networks, designed to accommodate small frame sizes on constrained wireless links. However, this process introduces a critical vulnerability fragments are typically…

Growing code bases of modern applications have led to a steady increase in the number of vulnerabilities. Control-Flow Integrity (CFI) is one promising mitigation that is more and more widely deployed and prevents numerous exploits. CFI…

Recent evidence suggests that frontier AI systems can exhibit agentic misalignment, generating and executing harmful actions derived from internally constructed goals, even without explicit user requests. Existing mitigation methods, such…

We introduce String Seed of Thought (SSoT), a novel prompting method for LLMs that improves Probabilistic Instruction Following (PIF). We define PIF as a task requiring an LLM to select its answer from a predefined set of options, each…

Man-At-The-End (MATE) attackers are almighty adversaries against whom there exists no silver-bullet countermeasure. To raise the bar, a wide range of protection measures were proposed in the literature each of which adds resilience against…

We present SEIF, a methodology that combines static analysis with symbolic execution to verify and explicate information flow paths in a hardware design. SEIF begins with a statically built model of the information flow through a design and…

Long-context LLMs can infer objectives that are not stated explicitly. This capability is useful for reasoning over documents, code, retrieved evidence, and tool traces, but it also creates a safety risk: harmful intent can be distributed…

Current adversarial attack research reveals the vulnerability of learning-based classifiers against carefully crafted perturbations. However, most existing attack methods have inherent limitations in cross-dataset generalization as they…

The rapid integration of Large Language Models (LLMs) into educational assessment rests on the unverified assumption that instruction following capability translates directly to objective adjudication. We demonstrate that this assumption is…

Semantic communication (SemCom) has emerged as a promising paradigm for next-generation networks. However, its typical end-to-end joint source--channel coding (JSCC) architecture also raises serious privacy concerns. To guide future secure…

Context: Large Language Models (LLMs) rely on static, pre-deployment safety mechanisms that cannot adapt to adversarial threats discovered after release. Objective: To design a software architecture enabling LLM-based systems to…

Safety alignment in large language models relies on behavioral training that can be overridden when sufficiently strong in-context patterns compete with learned refusal behaviors. We introduce Involuntary In-Context Learning (IICL), an…

Modern LLMs employ safety mechanisms that extend beyond surface-level input filtering to latent semantic representations and generation-time reasoning, enabling them to recover obfuscated malicious intent during inference and refuse…

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…

Intent detection, a core component of natural language understanding, has considerably evolved as a crucial mechanism in safeguarding large language models (LLMs). While prior work has applied intent detection to enhance LLMs' moderation…

Federated Learning (FL) facilitates collaborative model training while preserving data locality; however, the exchange of gradients renders the system vulnerable to Gradient Inversion Attacks (GIAs), allowing adversaries to reconstruct…

Memory-safety issues and information leakage are known to be depressingly common. We consider the compositional static detection of these kinds of vulnerabilities in first-order C-like programs. Indeed the latter are relational hyper-safety…

System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive…

To demonstrate and address the underlying maliciousness, we propose a theoretical hypothesis and analytical approach, and introduce a new black-box jailbreak attack methodology named IntentObfuscator, exploiting this identified flaw by…

The public accessibility of large vision-language models (LVLMs) raises serious concerns about unauthorized model reuse and intellectual property infringement. Existing ownership verification methods often rely on semantically abnormal…