Copertina

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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Mitra, Subhadip
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security Computation and Language Emerging Technologies Machine Learning Neural and Evolutionary Computing
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

NEUROSEC: FPGA-Based Neuromorphic Audio Security
di: Isik, Murat, et al.
Pubblicazione: (2024)

Language Modeling on a SpiNNaker 2 Neuromorphic Chip
di: Nazeer, Khaleelulla Khan, et al.
Pubblicazione: (2023)

MALT Powers Up Adversarial Attacks
di: Melamed, Odelia, et al.
Pubblicazione: (2024)

Cyber Risks to Next-Gen Brain-Computer Interfaces: Analysis and Recommendations
di: Schroder, Tyler, et al.
Pubblicazione: (2025)

Impact of White-Box Adversarial Attacks on Convolutional Neural Networks
di: Podder, Rakesh, et al.
Pubblicazione: (2024)

Integrated Security Mechanisms for Weight Protection in Memristive Crossbar Arrays
di: Rahman, Muhammad Faheemur, et al.
Pubblicazione: (2025)

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

Boosting Adversarial Robustness and Generalization with Structural Prior
di: Hou, Zhichao, et al.
Pubblicazione: (2025)

Physical Foundation Models: Fixed hardware implementations of large-scale neural networks
di: Wright, Logan G, et al.
Pubblicazione: (2026)

Analog Optical Inference on Million-Record Mortgage Data
di: Berloff, Sofia, et al.
Pubblicazione: (2026)

Insect-Wing Structured Microfluidic System for Reservoir Computing
di: Clouse, Jacob, et al.
Pubblicazione: (2025)

SpiNNaker2: A Large-Scale Neuromorphic System for Event-Based and Asynchronous Machine Learning
di: Gonzalez, Hector A., et al.
Pubblicazione: (2024)

Spatio-Temporal Pruning for Compressed Spiking Large Language Models
di: Jiang, Yi, et al.
Pubblicazione: (2025)

Gradient-descent hardware-aware training and deployment for mixed-signal Neuromorphic processors
di: Çakal, Uğurcan, et al.
Pubblicazione: (2023)

Reservoir Computing Benchmarks: a tutorial review and critique
di: Wringe, Chester, et al.
Pubblicazione: (2024)

Self-Adaptive Ising Machines for Constrained Optimization
di: Delacour, Corentin
Pubblicazione: (2025)

Training Deep Boltzmann Networks with Sparse Ising Machines
di: Niazi, Shaila, et al.
Pubblicazione: (2023)

Gradient descent in materia through homodyne gradient extraction
di: Boon, Marcus N., et al.
Pubblicazione: (2021)

Learning Dynamics in Memristor-Based Equilibrium Propagation
di: Döll, Michael, et al.
Pubblicazione: (2025)

Unsupervised End-to-End Training with a Self-Defined Target
di: Liu, Dongshu, et al.
Pubblicazione: (2024)

Transductive Spiking Graph Neural Networks for Loihi
di: Snyder, Shay, et al.
Pubblicazione: (2024)

A Path to Universal Neural Cellular Automata
di: Béna, Gabriel, et al.
Pubblicazione: (2025)

DelGrad: Exact event-based gradients for training delays and weights on spiking neuromorphic hardware
di: Göltz, Julian, et al.
Pubblicazione: (2024)

Deep Neuromorphic Networks with Superconducting Single Flux Quanta
di: Krylov, Gleb, et al.
Pubblicazione: (2023)

Neuromorphic on-chip reservoir computing with spiking neural network architectures
di: Karki, Samip, et al.
Pubblicazione: (2024)

Rectifying Adversarial Examples Using Their Vulnerabilities
di: Morimoto, Fumiya, et al.
Pubblicazione: (2026)

Adversarially Robust Spiking Neural Networks with Sparse Connectivity
di: Schmolli, Mathias, et al.
Pubblicazione: (2025)

On the Adversarial Robustness of Spiking Neural Networks Trained by Local Learning
di: Lin, Jiaqi, et al.
Pubblicazione: (2025)

BrainLeaks: On the Privacy-Preserving Properties of Neuromorphic Architectures against Model Inversion Attacks
di: Poursiami, Hamed, et al.
Pubblicazione: (2024)

Do Spikes Protect Privacy? Investigating Black-Box Model Inversion Attacks in Spiking Neural Networks
di: Poursiami, Hamed, et al.
Pubblicazione: (2025)

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

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

Multi-Task Wavelength-Multiplexed Reservoir Computing Using a Silicon Microring Resonator
di: Castro, Bernard J. Giron, et al.
Pubblicazione: (2023)

Monotone but Exciting: On Evolving Monotone Boolean Functions with High Nonlinearity
di: Carlet, Claude, et al.
Pubblicazione: (2026)

Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance
di: Rupa, Anamika Paul, et al.
Pubblicazione: (2026)

From One Attack Domain to Another: Contrastive Transfer Learning with Siamese Networks for APT Detection
di: Benabderrahmane, Sidahmed, et al.
Pubblicazione: (2025)

Attacking the Spike: On the Transferability and Security of Spiking Neural Networks to Adversarial Examples
di: Xu, Nuo, et al.
Pubblicazione: (2022)

Over-The-Air Extreme Learning Machines with XL Reception via Nonlinear Cascaded Metasurfaces
di: Stylianopoulos, Kyriakos, et al.
Pubblicazione: (2026)

RMAAT: Astrocyte-Inspired Memory Compression and Replay for Efficient Long-Context Transformers
di: Mia, Md Zesun Ahmed, et al.
Pubblicazione: (2026)