Search Results for author:
Found 11 papers, 2 papers with code
Projected Subnetworks Scale Adaptation
Large models support great zero-shot and few-shot capabilities.
Multiple Modes for Continual Learning
Adapting model parameters to incoming streams of data is a crucial factor to deep learning scalability.
Interpolating Compressed Parameter Subspaces
Inspired by recent work on neural subspaces and mode connectivity, we revisit parameter subspace sampling for shifted and/or interpolatable input distributions (instead of a single, unshifted distribution).
Low-Loss Subspace Compression for Clean Gains against Multi-Agent Backdoor Attacks
clean labels, which motivates this paper's work on the construction of multi-agent backdoor defenses that maximize accuracy w. r. t.
Backdoors Stuck At The Frontdoor: Multi-Agent Backdoor Attacks That Backfire
Malicious agents in collaborative learning and outsourced data collection threaten the training of clean models.
Hiding Behind Backdoors: Self-Obfuscation Against Generative Models
Attack vectors that compromise machine learning pipelines in the physical world have been demonstrated in recent research, from perturbations to architectural components.
Mind-proofing Your Phone: Navigating the Digital Minefield with GreaseTerminator
Digital harms are widespread in the mobile ecosystem.
Widen The Backdoor To Let More Attackers In
As collaborative learning and the outsourcing of data collection become more common, malicious actors (or agents) which attempt to manipulate the learning process face an additional obstacle as they compete with each other.
Exploring Design and Governance Challenges in the Development of Privacy-Preserving Computation
Homomorphic encryption, secure multi-party computation, and differential privacy are part of an emerging class of Privacy Enhancing Technologies which share a common promise: to preserve privacy whilst also obtaining the benefits of computational analysis.
Human-Computer Interaction
Like trainer, like bot? Inheritance of bias in algorithmic content moderation
This paper provides some exploratory methods by which the normative biases of algorithmic content moderation systems can be measured, by way of a case study using an existing dataset of comments labelled for offence.
