Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Rami Puzis

Rami Puzis

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Crypto×3ML×1AI×1

Frequent co-authors

Ofir Cohen2×
Asaf Shabtai2×
Xin Li1×
Chenhan Xiao1×
Jonathan Cohen1×
Aviad Elyashar1×

Research Timeline

2026
FreakOut-LLM: The Effect of Emotional Stimuli on Safety Alignment

This paper introduces FreakOut-LLM, demonstrating that emotional context, specifically stress, significantly compromises the safety alignment of large language models, increasing jailbreak susceptibility.

ConGISATA: A Framework for Continuous Gamified Information Security Awareness Training and Assessment

The paper proposes ConGISATA, a continuous, gamified framework using embedded mobile sensors to enhance individual information security awareness by transforming passive risks into active learning opportunities.

Cycle-Space Informed Detection of Autoencoded Blind False Data Injection Attacks on Power Systems

The paper proposes a Cycle-Space Detector (CSD) that uses network topology constraints to effectively detect stealthy, data-driven False Data Injection Attacks (FDIA) that exploit the null space of measurement data.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.CRRecentMay 27, 2026

Cycle-Space Informed Detection of Autoencoded Blind False Data Injection Attacks on Power Systems

Xin Li, Chenhan Xiao, Jonathan Cohen, Aviad Elyashar +2 more

The paper proposes a Cycle-Space Detector (CSD) that uses network topology constraints to effectively detect stealthy, data-driven False Data Injection Attacks (FDIA) that exploit the null space of me…

View →
cs.CRRecentApr 16, 2026

ConGISATA: A Framework for Continuous Gamified Information Security Awareness Training and Assessment

Ofir Cohen, Ron Bitton, Asaf Shabtai, Rami Puzis

The paper proposes ConGISATA, a continuous, gamified framework using embedded mobile sensors to enhance individual information security awareness by transforming passive risks into active learning opp…

View →
cs.CRcs.AIRecentApr 5, 2026

FreakOut-LLM: The Effect of Emotional Stimuli on Safety Alignment

Daniel Kuznetsov, Ofir Cohen, Karin Shistik, Rami Puzis +1 more

This paper introduces FreakOut-LLM, demonstrating that emotional context, specifically stress, significantly compromises the safety alignment of large language models, increasing jailbreak susceptibil…

View →