Image de couverture de livre

Cross-Generational Transfer of Adversarial Attacks Reveals Non-Monotonic Safety Alignment in LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Mitra, Subhadip
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security Computation and Language Emerging Technologies Machine Learning Neural and Evolutionary Computing
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Quality-Diversity Evolution for Discovering Diverse Vulnerabilities in LLM Safety
par: Mitra, Subhadip
Publié: (2026)

NEUROSEC: FPGA-Based Neuromorphic Audio Security
par: Isik, Murat, et autres
Publié: (2024)

Language Modeling on a SpiNNaker 2 Neuromorphic Chip
par: Nazeer, Khaleelulla Khan, et autres
Publié: (2023)

MALT Powers Up Adversarial Attacks
par: Melamed, Odelia, et autres
Publié: (2024)

Cyber Risks to Next-Gen Brain-Computer Interfaces: Analysis and Recommendations
par: Schroder, Tyler, et autres
Publié: (2025)

Impact of White-Box Adversarial Attacks on Convolutional Neural Networks
par: Podder, Rakesh, et autres
Publié: (2024)

Integrated Security Mechanisms for Weight Protection in Memristive Crossbar Arrays
par: Rahman, Muhammad Faheemur, et autres
Publié: (2025)

AI-Guided Codesign Framework for Novel Material and Device Design applied to MTJ-based True Random Number Generators
par: Patel, Karan P., et autres
Publié: (2024)

Boosting Adversarial Robustness and Generalization with Structural Prior
par: Hou, Zhichao, et autres
Publié: (2025)

Physical Foundation Models: Fixed hardware implementations of large-scale neural networks
par: Wright, Logan G, et autres
Publié: (2026)

Analog Optical Inference on Million-Record Mortgage Data
par: Berloff, Sofia, et autres
Publié: (2026)

Insect-Wing Structured Microfluidic System for Reservoir Computing
par: Clouse, Jacob, et autres
Publié: (2025)

SpiNNaker2: A Large-Scale Neuromorphic System for Event-Based and Asynchronous Machine Learning
par: Gonzalez, Hector A., et autres
Publié: (2024)

Spatio-Temporal Pruning for Compressed Spiking Large Language Models
par: Jiang, Yi, et autres
Publié: (2025)

Gradient-descent hardware-aware training and deployment for mixed-signal Neuromorphic processors
par: Çakal, Uğurcan, et autres
Publié: (2023)

Reservoir Computing Benchmarks: a tutorial review and critique
par: Wringe, Chester, et autres
Publié: (2024)

Self-Adaptive Ising Machines for Constrained Optimization
par: Delacour, Corentin
Publié: (2025)

Training Deep Boltzmann Networks with Sparse Ising Machines
par: Niazi, Shaila, et autres
Publié: (2023)

Gradient descent in materia through homodyne gradient extraction
par: Boon, Marcus N., et autres
Publié: (2021)

Learning Dynamics in Memristor-Based Equilibrium Propagation
par: Döll, Michael, et autres
Publié: (2025)

Unsupervised End-to-End Training with a Self-Defined Target
par: Liu, Dongshu, et autres
Publié: (2024)

Transductive Spiking Graph Neural Networks for Loihi
par: Snyder, Shay, et autres
Publié: (2024)

A Path to Universal Neural Cellular Automata
par: Béna, Gabriel, et autres
Publié: (2025)

DelGrad: Exact event-based gradients for training delays and weights on spiking neuromorphic hardware
par: Göltz, Julian, et autres
Publié: (2024)

Deep Neuromorphic Networks with Superconducting Single Flux Quanta
par: Krylov, Gleb, et autres
Publié: (2023)

Neuromorphic on-chip reservoir computing with spiking neural network architectures
par: Karki, Samip, et autres
Publié: (2024)

Rectifying Adversarial Examples Using Their Vulnerabilities
par: Morimoto, Fumiya, et autres
Publié: (2026)

Adversarially Robust Spiking Neural Networks with Sparse Connectivity
par: Schmolli, Mathias, et autres
Publié: (2025)

On the Adversarial Robustness of Spiking Neural Networks Trained by Local Learning
par: Lin, Jiaqi, et autres
Publié: (2025)

BrainLeaks: On the Privacy-Preserving Properties of Neuromorphic Architectures against Model Inversion Attacks
par: Poursiami, Hamed, et autres
Publié: (2024)

Do Spikes Protect Privacy? Investigating Black-Box Model Inversion Attacks in Spiking Neural Networks
par: Poursiami, Hamed, et autres
Publié: (2025)

The Conquest of Quantum Genetic Algorithms: The Adventure to Cross the Valley of Death
par: Lahoz-Beltra, Rafael
Publié: (2023)

Effects of cavity nonlinearities and linear losses on silicon microring-based reservoir computing
par: Castro, Bernard J. Giron, et autres
Publié: (2023)

Multi-Task Wavelength-Multiplexed Reservoir Computing Using a Silicon Microring Resonator
par: Castro, Bernard J. Giron, et autres
Publié: (2023)

Monotone but Exciting: On Evolving Monotone Boolean Functions with High Nonlinearity
par: Carlet, Claude, et autres
Publié: (2026)

Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance
par: Rupa, Anamika Paul, et autres
Publié: (2026)

From One Attack Domain to Another: Contrastive Transfer Learning with Siamese Networks for APT Detection
par: Benabderrahmane, Sidahmed, et autres
Publié: (2025)

Attacking the Spike: On the Transferability and Security of Spiking Neural Networks to Adversarial Examples
par: Xu, Nuo, et autres
Publié: (2022)

Over-The-Air Extreme Learning Machines with XL Reception via Nonlinear Cascaded Metasurfaces
par: Stylianopoulos, Kyriakos, et autres
Publié: (2026)

RMAAT: Astrocyte-Inspired Memory Compression and Replay for Efficient Long-Context Transformers
par: Mia, Md Zesun Ahmed, et autres
Publié: (2026)