MB
M. Backes
astro-ph.HEcs.CRcs.LGcs.AIastro-ph.IMcs.CVcs.CLastro-ph.COcs.CYstat.ML
On Valency
published · living versionsW_32e8cec4·v1 · currentpublished
A very-high-energy component deep in the Gamma-ray Burst afterglow
with H. Abdalla R. Adam F. Aharonian F. Ait Benkhali E. O. Anguener M. Arakawa, C. Arcaro, C. Armand, H. Ashkar +217
1 version
Preprints & journals
370 papers in the corpus · 2007–2026GeoCloak: An Agentic Framework for Semantics-Preserving Geolocation Privacy via Peripheral Clue Manipulation2610.20055v1 · Yixin Wu, Mingjie Li, Yun Shen et al.2026 · 0 citationsarXiv
MemeTrace: A Multimodal LLM-Based Agent for Safety-Aware Meme Provenance Analysis2610.19267v1 · Bo Shao, Yihan Ma, Yiting Qu et al.2026 · 0 citationsarXiv
No Free Efficiency: Revisiting the Trade-off Between Training Efficiency and Model Vulnerability2609.33898v1 · Yiyong Liu, Jun Sakuma, Michael Backes et al.2026 · 0 citationsarXiv
SADRA: Sound Capability-based Access Control System for Resource-Disaggregated Architectures2609.31119v1 · Hamed Rasifard, Amir Farahani Khojasteh, Hamed Nemati et al.2026 · 0 citationsarXiv
Optical spectroscopy of the VHE flat-spectrum radio quasar PKS 0903-572609.14999v1 · E. Kasai, P. Goldoni, C. Boisson et al.2026 · 0 citationsarXiv
"Shut Up and Let Me Enjoy My Otome": Understanding and Measuring the Toxicity in Otome Game Communities2609.08009v1 · Yage Zhang, Xinyue Shen, Yukun Jiang et al.2026 · 0 citationsarXiv
AgentProv: Auditing Agentic LLM API Providers via Tool-use Policy Probes2609.00052v1 · Xun Wang, Bihe Zhao, Michael Backes et al.2026 · 0 citationsarXiv
Evidence for a spectral steepening of the gamma-ray emission from the Galactic Center ridge2608.25946v1 · A. Acharyya, F. Aharonian, H. Ashkar et al.2026 · 0 citationsarXiv
Size, shape, density, and atmospheric limit of (50000) Quaoar revealed from 14 years of stellar occultation2607.06450v1 · Giuliano Margoti, Felipe Braga-Ribas, Jos'e Luis Ortiz et al.2026 · 0 citationsarXiv
Broadband multiwavelength properties of the archetypal blazar 3C 279 during the 2017 Event Horizon Telescope campaign2606.25868v2 · G. Principe, J. C. Algaba, E. Aviano et al.2026 · 0 citationsA&A, 712, A224 (2026)
MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning2606.22220v2 · Wenhao Wang, Franziska Boenisch, Michael Backes et al.2026 · 0 citationsarXiv
PeerCheck: Enhancing LLM-Generated Academic Reviews Towards Human-Level Quality2606.20897v1 · Zeyuan Chen, Ziqing Yang, Yihan Ma et al.2026 · 0 citationsarXiv
Gamma-Ray Constraints on Heavy Axion-Like-Particle Decays from Fermi-LAT and H.E.S.S. Blazar Spectra2606.11923v1 · A. Acharyya, F. Aharonian, M. Backes et al.2026 · 0 citationsarXiv
Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models2606.09401v1 · Bart\lomiej Marek, Lorenzo Rossi, Vincent Hanke et al.2026 · 0 citationsarXiv
BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning2605.31246v1 · Ziqing Yang, Rui Wen, Xinlei He et al.2026 · 0 citationsarXiv
Search for long-term variability of HESS J1745-2902605.10827v1 · F. Aharonian, M. Backes, R. Batzofin et al.2026 · 0 citationsA&A, 709, A96 (2026)
Trust Me, Import This: Dependency Steering Attacks via Malicious Agent Skills2605.09594v1 · Yiyong Liu, Chia-Yi Hsu, Chun-Ying Huang et al.2026 · 0 citationsarXiv
Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models2605.06423v1 · Zeyuan Chen, Yihan Ma, Xinyue Shen et al.2026 · 0 citationsarXiv
SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts2604.26506v2 · Yuan Xin, Yixuan Weng, Minjun Zhu et al.2026 · 0 citationsarXiv
Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs2604.15780v1 · Wai Man Si, Mingjie Li, Michael Backes et al.2026 · 0 citationsarXiv
A Systematic Study of Training-Free Methods for Trustworthy Large Language Models2604.15789v1 · Wai Man Si, Mingjie Li, Michael Backes et al.2026 · 0 citationsarXiv
HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?2604.15415v1 · Yukun Jiang, Yage Zhang, Michael Backes et al.2026 · 0 citationsarXiv
TrustLDM: Benchmarking Trustworthiness in Language Diffusion Models2606.00023v1 · Yichuan Mo, Yukun Jiang, Yanbo Shi et al.2026 · 0 citationsarXiv
The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training2604.07754v1 · Rui Zhang, Hongwei Li, Yun Shen et al.2026 · 0 citationsarXiv
OrgAgent: Organize Your Multi-Agent System like a Company2604.01020v1 · Yiru Wang, Xinyue Shen, Yaohui Han et al.2026 · 0 citationsarXiv
When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm2603.24079v1 · Ye Leng, Junjie Chu, Mingjie Li et al.2026 · 0 citationsarXiv
H.E.S.S. observations of composite Seyfert-starburst galaxies2603.21912v1 · A. Acharyya, F. Aharonian, H. Ashkar et al.2026 · 0 citationsarXiv
Scrutinizing the 2020 multiwavelength outburst of PKS 0903-57 through observations with H.E.S.S2603.12855v1 · A. Acharyya, F. Aharonian, F. Ait Benkhali et al.2026 · 0 citationsarXiv
Understanding LLM Behavior When Encountering User-Supplied Harmful Content in Harmless Tasks2603.11914v1 · Junjie Chu, Yiting Qu, Ye Leng et al.2026 · 0 citationsarXiv
Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms2604.00012v1 · Mingjie Li, Wai Man Si, Michael Backes et al.2026 · 0 citationsarXiv
Benchmark of Benchmarks: Unpacking Influence and Code Repository Quality in LLM Safety Benchmarks2603.04459v3 · Junjie Chu, Xinyue Shen, Ye Leng et al.2026 · 0 citationsarXiv
Real Money, Fake Models: Deceptive Model Claims in Shadow APIs2603.01919v3 · Yage Zhang, Yukun Jiang, Zeyuan Chen et al.2026 · 0 citationsarXiv
H.E.S.S. detection of the PSR J0855-4644 nebula2602.14640v1 · F. Aharonian, H. Ashkar, M. Backes et al.2026 · 1 citationarXiv
Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs2602.08621v1 · Yukun Jiang, Hai Huang, Mingjie Li et al.2026 · 0 citationsarXiv
"Humans welcome to observe": A First Look at the Agent Social Network Moltbook2602.10127v1 · Yukun Jiang, Yage Zhang, Xinyue Shen et al.2026 · 0 citationsarXiv
Revisiting Transferable Adversarial Images: Systemization, Evaluation, and New Insights.40956694 · Zhao, Zhengyu, Zhang, Hanwei, Li, Renjue et al.2025 · 15 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(1):765-780
Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race?2512.24044v1 · Yuan Xin, Dingfan Chen, Linyi Yang et al.2025 · 0 citationsarXiv
Prompt Searches for Very-High-Energy {\gamma}-Ray Counterparts to IceCube Astrophysical Neutrino Alerts2512.16562v1 · J. Abhir, A. Biland, K. Brand et al.2025 · 1 citationarXiv
GEO-Detective: Unveiling Location Privacy Risks in Images with LLM Agents2511.22441v1 · Xinyu Zhang, Yixin Wu, Boyang Zhang et al.2025 · 1 citationarXiv
AttackPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agents2511.19536v1 · Yixin Wu, Rui Wen, Chi Cui et al.2025 · 0 citationsarXiv
Constraining the nature of the most extreme Galactic particle accelerator. H.E.S.S. observations of the microquasar V4641 Sgr2511.10537v1 · A. Acharyya, F. Aharonian, H. Ashkar et al.2025 · 1 citationarXiv
From Evidence to Verdict: An Agent-Based Forensic Framework for AI-Generated Image Detection2511.00181v2 · Mengfei Liang, Yiting Qu, Yukun Jiang et al.2025 · 0 citationsarXiv
Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency2510.21189v1 · Yukun Jiang, Mingjie Li, Michael Backes et al.2025 · 1 citationarXiv
JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring2508.20848v1 · Junjie Chu, Mingjie Li, Ziqing Yang et al.2025 · 0 citationsarXiv
Combined dark matter search towards dwarf spheroidal galaxies with Fermi-LAT, HAWC, H.E.S.S., MAGIC, and VERITAS2508.20229v1 · S. Abdollahi, L. Baldini, R. Bellazzini et al.2025 · 5 citationsarXiv
Prospects for dark matter observations in dwarf spheroidal galaxies with the Cherenkov Telescope Array Observatory2508.19120v3 · K. Abe, S. Abe, J. Abhir et al.2025 · 3 citationsMon Not R Astron Soc (2025) 2946-2986
Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions2507.22617v1 · Yiting Qu, Ziqing Yang, Yihan Ma et al.2025 · 0 citationsarXiv
Optical spectroscopy of blazars for the Cherenkov Telescope Array Observatory- IV2507.14993v1 · B. Rajput, P. Goldoni, W. Max-Moerbeck et al.2025 · 1 citationA&A 704, A190 (2025)
Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities2507.11155v1 · Yiting Qu, Michael Backes, Yang Zhang2025 · 0 citationsarXiv
Rethinking Data Protection in the (Generative) Artificial Intelligence Era2507.03034v4 · Yiming Li, Shuo Shao, Yu He et al.2025 · 1 citationarXiv
Career total: 1352 works. 370 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.