Imagen de Portada

Facial Misrecognition Systems: Simple Weight Manipulations Force DNNs to Err Only on Specific Persons

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zehavi, Irad, Nitzan, Roee, Shamir, Adi
Formato:	Preprint
Publicado:	2023
Materias:	Cryptography and Security Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

MALT Powers Up Adversarial Attacks
por: Melamed, Odelia, et al.
Publicado: (2024)

To Err is Machine: Vulnerability Detection Challenges LLM Reasoning
por: Steenhoek, Benjamin, et al.
Publicado: (2024)

Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions
por: Prato, Tahmid Hasan, et al.
Publicado: (2025)

Authority Backdoor: A Certifiable Backdoor Mechanism for Authoring DNNs
por: Yang, Han, et al.
Publicado: (2025)

Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks
por: Kuo, Kevin, et al.
Publicado: (2026)

Temporal Contrastive Transformer for Financial Crime Detection: Self-Supervised Sequence Embeddings via Predictive Contrastive Coding
por: Butvinik, Danny, et al.
Publicado: (2026)

Relationship between Uncertainty in DNNs and Adversarial Attacks
por: Ogonna, Mabel, et al.
Publicado: (2024)

Reformulation is All You Need: Addressing Malicious Text Features in DNNs
por: Jiang, Yi, et al.
Publicado: (2025)

Assessing the Resilience of Automotive Intrusion Detection Systems to Adversarial Manipulation
por: Longari, Stefano, et al.
Publicado: (2025)

TruncFormer: Private LLM Inference Using Only Truncations
por: Yubeaton, Patrick, et al.
Publicado: (2024)

Federated Learning with Only Positive Labels by Exploring Label Correlations
por: An, Xuming, et al.
Publicado: (2024)

Approaching the Harm of Gradient Attacks While Only Flipping Labels
por: El-Kabid, Abdessamad, et al.
Publicado: (2025)

OSLO: One-Shot Label-Only Membership Inference Attacks
por: Peng, Yuefeng, et al.
Publicado: (2024)

Adversarial Sample-Based Approach for Tighter Privacy Auditing in Final Model-Only Scenarios
por: Yoon, Sangyeon, et al.
Publicado: (2024)

LoMime: Query-Efficient Membership Inference using Model Extraction in Label-Only Settings
por: Oksuz, Abdullah Caglar, et al.
Publicado: (2026)

GESR: Graph-Based Edge Semantic Reconstruction for Stealthy Communication Detection with Benign-Only Training
por: Xu, Henghui, et al.
Publicado: (2026)

Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable
por: Bertran, Martin, et al.
Publicado: (2024)

DCInject: Persistent Backdoor Attacks via Frequency Manipulation in Personal Federated Learning
por: Birhan, Nahom, et al.
Publicado: (2026)

The 'Sure' Trap: Multi-Scale Poisoning Analysis of Stealthy Compliance-Only Backdoors in Fine-Tuned Large Language Models
por: Tan, Yuting, et al.
Publicado: (2025)

Simple and Efficient Partial Graph Adversarial Attack: A New Perspective
por: Zhu, Guanghui, et al.
Publicado: (2023)

Simple Perturbations Subvert Ethereum Phishing Transactions Detection: An Empirical Analysis
por: Alghureid, Ahod, et al.
Publicado: (2024)

DeepCore: Simple Fingerprint Construction for Differentiating Homologous and Piracy Models
por: Sun, Haifeng, et al.
Publicado: (2024)

Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards
por: Huang, Yangsibo, et al.
Publicado: (2025)

Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense
por: Ma, Hua, et al.
Publicado: (2023)

Attack Anything: Blind DNNs via Universal Background Adversarial Attack
por: Lian, Jiawei, et al.
Publicado: (2024)

Limits of Personalizing Differential Privacy Budgets
por: Cyffers, Edwige, et al.
Publicado: (2026)

Weights Shuffling for Improving DPSGD in Transformer-based Models
por: Yang, Jungang, et al.
Publicado: (2024)

SLIP: Securing LLMs IP Using Weights Decomposition
por: Refael, Yehonathan, et al.
Publicado: (2024)

Verifying LLM Inference to Detect Model Weight Exfiltration
por: Rinberg, Roy, et al.
Publicado: (2025)

Uncovering and Understanding FPR Manipulation Attack in Industrial IoT Networks
por: Ahsan, Mohammad Shamim, et al.
Publicado: (2026)

Exploiting Unstructured Sparsity in Fully Homomorphic Encrypted DNNs
por: Ferguson, Aidan, et al.
Publicado: (2025)

Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification
por: Schuchardt, Jan, et al.
Publicado: (2024)

Personalized Privacy Amplification via Importance Sampling
por: Fay, Dominik, et al.
Publicado: (2023)

TokenBreak: Bypassing Text Classification Models Through Token Manipulation
por: Schulz, Kasimir, et al.
Publicado: (2025)

ARQ: A Mixed-Precision Quantization Framework for Accurate and Certifiably Robust DNNs
por: Yang, Yuchen, et al.
Publicado: (2024)

Fine-tuning of Large Language Models for Domain-Specific Cybersecurity Knowledge
por: Huang, Yuan
Publicado: (2025)

RL Is a Hammer and LLMs Are Nails: A Simple Reinforcement Learning Recipe for Strong Prompt Injection
por: Wen, Yuxin, et al.
Publicado: (2025)

Mitigating Membership Inference Vulnerability in Personalized Federated Learning
por: Jung, Kangsoo, et al.
Publicado: (2025)

The SkipSponge Attack: Sponge Weight Poisoning of Deep Neural Networks
por: Lintelo, Jona te, et al.
Publicado: (2024)

RAIFLE: Reconstruction Attacks on Interaction-based Federated Learning with Adversarial Data Manipulation
por: Pham, Dzung, et al.
Publicado: (2023)