FS
Fnu Suya
cs.CRcs.LGcs.AIcs.CVcs.CLstat.MLcs.IRcs.SDeess.AS
On Valency
published · living versionsW_zs8p4n3z·v1 · currentpublished
PROVISO: Provenance-Informed Action Selection for Secure LLM Agents
with Bo Yan, Qi Zhang, Ziwen Kan, Song Wang
1 version
Preprints & journals
20 papers in the corpus · 2017–2026PROVISO: Provenance-Informed Action Selection for Secure LLM Agents2610.27115v1 · Bo Yan, Qi Zhang, Ziwen Kan et al.2026 · 0 citationsarXivon Valency
Greedy Decoding Is Not Precision-Invariant: Cross-Precision Output Divergence in LLM Inference2609.26621v1 · Gaoyuan Du, Anam Nawaz Khan, Rex Zhou et al.2026 · 0 citationsTransactions on Machine Learning Research, 2026
Hearing the Whispers: Black-Box Membership Inference Attacks on Finetuned TTS Models2609.01723v1 · Kunlin Cai, Kaiyuan Zhang, Zihang Xiang et al.2026 · 0 citationsarXiv
(A)iSpy: Parasitic Trojans for Machine Learning Infrastructure2607.17550v2 · Habibur Rahaman, Qipan Xu, Zafaryab Haider et al.2026 · 0 citationsarXiv
ImageAuditor: Membership Inference Attack against Image-based Retrieval-Augmented Generation2606.03354v1 · Jinghuai Zhang, Pengyue Yu, Zhexiao Lin et al.2026 · 0 citationsarXiv
Token Inflation: How Dishonest Providers Can Overcharge for Large Language Model Usage2605.30040v1 · Shahinul Hoque, Jinghuai Zhang, Jinyuan Sun et al.2026 · 0 citationsarXiv
What-If World: A Causal Benchmark for General World Models in Embodied Scenarios2605.27589v1 · Kunlin Cai, Rui Song, Jinghuai Zhang et al.2026 · 0 citationsarXiv
LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models2605.21362v1 · Abdullah Al Nomaan Nafi, Fnu Suya, Swarup Bhunia et al.2026 · 0 citationsarXiv
HAMLOCK: HArdware-Model LOgically Combined attacK2510.19145v4 · Sanskar Amgain, Daniel Lobo, Atri Chatterjee et al.2025 · 0 citationsarXiv
DASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examples2508.13309v4 · Abdullah Al Nomaan Nafi, Habibur Rahaman, Zafaryab Haider et al.2025 · 0 citationsarXiv
Adversarial Hubness in Multi-Modal Retrieval2412.14113v4 · Tingwei Zhang, Fnu Suya, Rishi Jha et al.2024 · 1 citationarXiv
Understanding Variation in Subpopulation Susceptibility to Poisoning Attacks2311.11544v1 · Evan Rose, Fnu Suya, David Evans2023 · 0 citationsarXiv
SoK: Pitfalls in Evaluating Black-Box Attacks2310.17534v2 · Fnu Suya, Anshuman Suri, Tingwei Zhang et al.2023 · 3 citationsarXiv
What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners?2307.01073v2 · Fnu Suya, Xiao Zhang, Yuan Tian et al.2023 · 0 citationsarXiv
Manipulating Transfer Learning for Property Inference2303.11643v1 · Yulong Tian, Fnu Suya, Anshuman Suri et al.2023 · 7 citationsarXiv
Stealthy Backdoors as Compression Artifacts2104.15129v1 · Yulong Tian, Fnu Suya, Fengyuan Xu et al.2021 · 28 citationsarXiv
Model-Targeted Poisoning Attacks with Provable Convergence2006.16469v2 · Fnu Suya, Saeed Mahloujifar, Anshuman Suri et al.2020 · 16 citationsarXiv
Scalable Attack on Graph Data by Injecting Vicious Nodes2004.13825v1 · Jihong Wang, Minnan Luo, Fnu Suya et al.2020 · 75 citationsarXiv
Hybrid Batch Attacks: Finding Black-box Adversarial Examples with Limited Queries1908.07000v3 · Fnu Suya, Jianfeng Chi, David Evans et al.2019 · 54 citationsarXiv
Query-limited Black-box Attacks to Classifiers1712.08713v1 · Fnu Suya, Yuan Tian, David Evans et al.2017 · 12 citationsarXiv
Career total: 27 works. 20 are in this corpus.
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.