LLMs remain vulnerable to prompt injection attacks, where adversarial instructions embedded in user inputs or external content manipulate model behavior and bypass safeguards. Existing defenses are predominantly static, relying on fixed alignment objectives or attack-specific filtering mechanisms that require redesign...
Large Language Models (LLMs) are highly effective for cybersecurity question answering (QA) but are difficult to deploy on edge devices due to their size. Quantization reduces memory and compute requirements but often degrades accuracy and increases vulnerability to adversarial attacks. We present EAGER, an edge-aligne...
Onat Gungor, Roshan Sood, Jia-Sheng Zhou et al.· International Symposium on N...· 0 citations
T-SMART is presented, a neurosymbolic framework that separates these roles: a frozen LLM interprets questions and selects operations, deterministic tools perform numerical computation, and structured perception is invoked only when needed to provide a controlled framework for analyzing component contributions in neuros...
I. Delgado, Himansi Gupta, B. Khatri et al.· 0 citations
LIMBO is introduced, the first online framework to the authors' knowledge that treats memory as a controllable inference-time resource and jointly optimizes memory strategy and inference budget for each incoming task, and learns this allocation online in a single pass.
Siddharth Sharma, N. Pandey, Onat Gungor et al.· 1 citation
LifeAgent is proposed, a tool-augmented reasoning baseline that decomposes complex queries, performs multi-step evidence retrieval, and invokes tools for deterministic aggregation that substantially enhances LLMs'capabilities on challenging reasoning tasks, achieving clear improvements over widely used baselines and sh...
Ye Tian, Zihao Wang, Onat Gungor et al.· 0 citations
ReLATE+ is proposed, a unified framework for adversarially robust and computationally efficient time-series classification that ensures strong performance while reducing the need for retraining, and it generalizes well across different domains with varying data distributions and feature spaces.
C. I. Kocal, Onat Gungor, T. Rosing et al.· Electronics· 0 citations
G-MARK is proposed, a grounded multi-agent reasoning framework that converts cooperative object-centric observations into explicit provenance-aware knowledge graphs (KGs) that preserve object hypotheses together with their source attribution, ego-versus-partner visibility, uncertainty, conflicts, spatial relations, and...
B. Gupta, Onat Gungor, T. Rosing· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
