Research
Research
Research
Research
6,992+ open-access research outputs.
Multi-turn prompt injection follows a known attack path -- trust-building, pivoting, escalation but text-level defenses miss covert attacks where individual turns appear benign. We show this attack pa…
The problem of determining whether a probabilistic program terminates almost surely (i.e.~with probability one) is undecidable, and actually $\Pi^0_2$-complete. For this reason, a growing literature h…
In Mixed-Criticality (MC) systems, although the high Worst-Case Execution Time (WCET) serves as a conservative upper bound representing the task's maximum execution time under all conditions, obtainin…
Decompositional jailbreaks pose a critical threat to large language models (LLMs) by allowing adversaries to fragment a malicious objective into a sequence of individually benign queries that collecti…
LLMs are increasingly employed both as judges for evaluating open-ended outputs and as co-creation partners in AI-assisted programming; yet rigorous evaluation in human-AI co-creation settings remains…
Large language model (LLM) agents are increasingly deployed in social settings, yet little is known about how they interact in open-ended environments. We present the first comprehensive sociological …
Coded caching is a technique that leverages locally cached contents at the end users to reduce the network's peak-time communication load. Coded caching has been shown to achieve significant performan…
Despite the operational importance of hot fixes, large-scale evidence on how they reshape routine maintenance workflows, particularly in the era of autonomous coding agents, remains limited. We analys…
Process malleability has proved to have a highly positive impact on the resource utilization and global productivity in data centers compared with the conventional static resource allocation policy. H…
Differentially private (DP) contrastive learning aims to learn general-purpose representations from sensitive data, alleviating the privacy leakage concerns of organizations deploying or sharing embed…
AI coding agents demonstrate strong performance on general-purpose software benchmarks. However, their ability to handle 5G network engineering tasks remains unexplored. We propose SWE-Bench~5G, the f…
Structured-workflow agents driven by large language models execute tool calls against sensitive external environments. We propose \codename, a telemetry-driven behavioral anomaly detection firewall. D…
Web agents have emerged as an effective paradigm for automating interactions with complex web environments, yet remain vulnerable to prompt injection attacks that embed malicious instructions into web…
Despite strong performance on code generation tasks, it remains unclear whether large language models (LLMs) genuinely reason about code execution. Existing code reasoning benchmarks primarily evaluat…
Foundation models are routinely fine-tuned for use in particular domains, yet safety assessments are typically conducted only on base models, implicitly assuming that safety properties persist through…
We propose a new convex programming relaxation for the weighted Nash social welfare (NSW) problem that achieves a matching $(e^{1/e}\approx 1.445)$-approximation via the rounding algorithm of Feng and…
Large (vision-)language models exhibit remarkable capability but remain highly susceptible to jailbreaking. Existing safety training approaches aim to have the model learn a refusal boundary between s…
Gate elimination is the primary technique for proving explicit lower bounds against general Boolean circuits, including Li and Yang's state-of-the-art $3.1n - o(n)$ bound for affine dispersers (STOC 2…
The global financial ecosystem confronts a critical asymmetry: while fraud syndicates operate as borderless, distributed networks, banking institutions remain constrained by regulatory data silos, lim…
Research shows that dialogue, the interactive process through which participants articulate their thinking, plays a central role in constructing shared understanding, coordinating action, and shaping …
Free open-access publishing with Google Scholar indexing.
Submission Guide →