Image de couverture de livre

FeatureBleed: Inferring Private Enriched Attributes From Sparsity-Optimized AI Accelerators

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Asher, Darsh, Dizani, Farshad, Kalyanapu, Joshua, Cammarota, Rosario, Aysu, Aydin, Ajorpaz, Samira Mirbagher
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

GATEBLEED: Exploiting On-Core Accelerator Power Gating for High Performance & Stealthy Attacks on AI
par: Kalyanapu, Joshua, et autres
Publié: (2025)

THOR: A Non-Speculative Value Dependent Timing Side Channel Attack Exploiting Intel AMX
par: Dizani, Farshad, et autres
Publié: (2025)

Stochastic Training for Side-Channel Resilient AI
par: Dubey, Anuj, et autres
Publié: (2025)

SHIFT SNARE: Uncovering Secret Keys in FALCON via Single-Trace Analysis
par: Qiu, Jinyi, et autres
Publié: (2025)

CacheMind: From Miss Rates to Why -- Natural-Language, Trace-Grounded Reasoning for Cache Replacement
par: Mhapsekar, Kaushal, et autres
Publié: (2026)

Honest to a Fault: Root-Causing Fault Attacks with Pre-Silicon RISC Pipeline Characterization
par: Malik, Arsalan Ali, et autres
Publié: (2025)

CRAFT: Characterizing and Root-Causing Fault Injection Threats at Pre-Silicon
par: Malik, Arsalan Ali, et autres
Publié: (2025)

Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction Attacks
par: Kurian, Ashley, et autres
Publié: (2025)

Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsity
par: Yan, Guang, et autres
Publié: (2025)

Earn While You Reveal: Private Set Intersection that Rewards Participants
par: Abadi, Aydin
Publié: (2023)

Hardware-Enabled Mechanisms for Verifying Responsible AI Development
par: O'Gara, Aidan, et autres
Publié: (2025)

Differentially Private Linear Optimization for Multi-Party Resource Sharing
par: Karaca, Utku, et autres
Publié: (2021)

Decode and Forward Relaying for SC-FDE Systems with a Multi-Antenna Relay
par: Dizani, Farshad, et autres
Publié: (2025)

Inferring Sensitive Attributes from Knowledge Graph Embeddings: Attack and Defense Strategies
par: Hayder, Yasmine
Publié: (2026)

CIA+TA Risk Assessment for AI Reasoning Vulnerabilities
par: Aydin, Yuksel
Publié: (2025)

I Can Tell Your Secrets: Inferring Privacy Attributes from Mini-app Interaction History in Super-apps
par: Cai, Yifeng, et autres
Publié: (2025)

Locally Private Estimation with Public Features
par: Ma, Yuheng, et autres
Publié: (2024)

Differentially Private Random Feature Model
par: Liao, Chunyang, et autres
Publié: (2024)

Enhancing Pre-Trained Language Models for Vulnerability Detection via Semantic-Preserving Data Augmentation
par: Qi, Weiliang, et autres
Publié: (2024)

HetDAPAC: Leveraging Attribute Heterogeneity in Distributed Attribute-Based Private Access Control
par: Meel, Shreya, et autres
Publié: (2025)

Accelerating Private Large Transformers Inference through Fine-grained Collaborative Computation
par: Chen, Yuntian, et autres
Publié: (2024)

Generative AI for Critical Infrastructure in Smart Grids: A Unified Framework for Synthetic Data Generation and Anomaly Detection
par: Zaboli, Aydin, et autres
Publié: (2025)

HetDAPAC: Distributed Attribute-Based Private Access Control with Heterogeneous Attributes
par: Meel, Shreya, et autres
Publié: (2024)

On the Gradient Complexity of Private Optimization with Private Oracles
par: Menart, Michael, et autres
Publié: (2025)

Opal: Private Memory for Personal AI
par: Kaviani, Darya, et autres
Publié: (2026)

On Design Principles for Private Adaptive Optimizers
par: Ganesh, Arun, et autres
Publié: (2025)

Hyena: Optimizing Homomorphically Encrypted Convolution for Private CNN Inference
par: Roh, Hyeri, et autres
Publié: (2023)

Privacy-Optimized Randomized Response for Sharing Multi-Attribute Data
par: Yamamoto, Akito, et autres
Publié: (2024)

Inferentially-Private Private Information
par: Wang, Shuaiqi, et autres
Publié: (2024)

SHIELD: A Host-Independent Framework for Ransomware Detection using Deep Filesystem Features
par: Raz, Md, et autres
Publié: (2025)

"Think First, Verify Always": Training Humans to Face AI Risks
par: Aydin, Yuksel
Publié: (2025)

Safeguarding LLMs Against Misuse and AI-Driven Malware Using Steganographic Canaries
par: Raz, Md, et autres
Publié: (2026)

Private Map-Secure Reduce: Infrastructure for Efficient AI Data Markets
par: Wagh, Sameer, et autres
Publié: (2025)

Enabling Deep Visibility into VxWorks-Based Embedded Controllers in Cyber-Physical Systems for Anomaly Detection
par: Krishnamurthy, Prashanth, et autres
Publié: (2025)

SCAMPER -- Synchrophasor Covert chAnnel for Malicious and Protective ERrands
par: Krishnamurthy, Prashanth, et autres
Publié: (2025)

Real-Time Multi-Modal Subcomponent-Level Measurements for Trustworthy System Monitoring and Malware Detection
par: Khorrami, Farshad, et autres
Publié: (2025)

Optimized Tradeoffs for Private Prediction with Majority Ensembling
par: Jiang, Shuli, et autres
Publié: (2024)

Differentially Private Decentralized Optimization with Relay Communication
par: Wang, Luqing, et autres
Publié: (2022)

S-BDT: Distributed Differentially Private Boosted Decision Trees
par: Peinemann, Thorsten, et autres
Publié: (2023)

Differentially Private Bilevel Optimization
par: Kornowski, Guy
Publié: (2024)