Institution profile

Keysight Technologies

Industry researchnorthamerica · us
Official website
Research library7linked papers
Opportunities0open roles
Selected work

Representative Papers

Hardware-in-the-Loop Phase-Aware CNN for Real-Time 5G Channel Estimation

Aug 11, 2026

This study addresses performance degradation caused by hardware impairments and the challenges of deploying real-time AI inference in 5G uplink channel estimation. We establish an O-RAN hardware-in-the-loop platform and propose a DMRS-based phase-aware CNN alongside an AI-native physical layer inference workflow. By leveraging a lightweight network trained on empirical hardware data, this approach enables real-time channel estimation that effectively mitigates RF non-idealities. Experimental results demonstrate that the proposed method achieves high-precision, real-time channel reconstruction under realistic hardware impairments, significantly outperforming conventional LS and LMMSE baselines. These findings validate the feasibility and robustness of AI-native architectures for practical deployment in future 6G networks, bridging the gap between theoretical AI models and real-world physical layer implementation.

0 citationsRead paper

Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems

Jun 18, 2026

Traditional defense mechanisms are vulnerable to model-guided automated attacks due to their predictable rejection feedback, enabling high-success-rate jailbreaks and prompt injection threats against AI systems. This work proposes a novel “mislead-after-detection” paradigm that shifts the defensive objective from complete attack blocking to reducing the efficiency of attackers’ strategy optimization by generating safe yet misleading responses to confound adversarial judgment. Leveraging probabilistic modeling, we design a lightweight Contextual Misleading via Probabilistic Estimation (CMPE) mechanism and theoretically prove that it asymptotically bounds attack success rates. Evaluated on standard jailbreaking benchmarks, CMPE reduces the upper bound of attack success rates by up to two orders of magnitude, effectively eliminating nearly all successful end-to-end automated attacks.

0 citationsRead paper
Recent publications

Latest Papers

Hardware-in-the-Loop Phase-Aware CNN for Real-Time 5G Channel Estimation

Aug 11, 2026

This study addresses performance degradation caused by hardware impairments and the challenges of deploying real-time AI inference in 5G uplink channel estimation. We establish an O-RAN hardware-in-the-loop platform and propose a DMRS-based phase-aware CNN alongside an AI-native physical layer inference workflow. By leveraging a lightweight network trained on empirical hardware data, this approach enables real-time channel estimation that effectively mitigates RF non-idealities. Experimental results demonstrate that the proposed method achieves high-precision, real-time channel reconstruction under realistic hardware impairments, significantly outperforming conventional LS and LMMSE baselines. These findings validate the feasibility and robustness of AI-native architectures for practical deployment in future 6G networks, bridging the gap between theoretical AI models and real-world physical layer implementation.

0 citationsRead paper

Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems

Jun 18, 2026

Traditional defense mechanisms are vulnerable to model-guided automated attacks due to their predictable rejection feedback, enabling high-success-rate jailbreaks and prompt injection threats against AI systems. This work proposes a novel “mislead-after-detection” paradigm that shifts the defensive objective from complete attack blocking to reducing the efficiency of attackers’ strategy optimization by generating safe yet misleading responses to confound adversarial judgment. Leveraging probabilistic modeling, we design a lightweight Contextual Misleading via Probabilistic Estimation (CMPE) mechanism and theoretically prove that it asymptotically bounds attack success rates. Evaluated on standard jailbreaking benchmarks, CMPE reduces the upper bound of attack success rates by up to two orders of magnitude, effectively eliminating nearly all successful end-to-end automated attacks.

0 citationsRead paper