26 citations · 42 across the 20 of their papers we have counts for
20 papers
Auditing Preferences for Brands and Cultures in LLMs
Jasmine Rienecker, Katarina Mpofu, Naman Goel +4
Large language models (LLMs) based AI systems increasingly mediate what billions of people see, choose and buy. This creates an urgent need to quantify the systemic risks of LLM-dr…
Not Even Nice Work If You Can Get It; A Longitudinal Study of Uber's Algorithmic Pay and Pricing
Reuben Binns, Jake Stein, Siddhartha Datta +2
Ride-sharing platforms like Uber market themselves as enabling `flexibility' for their workforce, meaning that drivers are expected to anticipate when and where the algorithm will…
DiffuBox: Refining 3D Object Detection with Point Diffusion
Xiangyu Chen, Zhenzhen Liu, Katie Z Luo +10
Ensuring robust 3D object detection and localization is crucial for many applications in robotics and autonomous driving. Recent models, however, face difficulties in maintaining h…
Online Feature Updates Improve Online (Generalized) Label Shift Adaptation
Ruihan Wu, Siddhartha Datta, Yi Su +3
This paper addresses the prevalent issue of label shift in an online setting with missing labels, where data distributions change over time and obtaining timely labels is challengi…
Prompt Expansion for Adaptive Text-to-Image Generation
Siddhartha Datta, Alexander Ku, Deepak Ramachandran +1
Text-to-image generation models are powerful but difficult to use. Users craft specific prompts to get better images, though the images can be repetitive. This paper proposes a Pro…
Projected Subnetworks Scale Adaptation
Siddhartha Datta, Nigel Shadbolt
Large models support great zero-shot and few-shot capabilities. However, updating these models on new tasks can break performance on previous seen tasks and their zero/few-shot uns…
Cross-Reality Re-Rendering: Manipulating between Digital and Physical Realities
Siddhartha Datta
The advent of personalized reality has arrived. Rapid development in AR/MR/VR enables users to augment or diminish their perception of the physical world. Robust tooling for digita…
Multiple Modes for Continual Learning
Siddhartha Datta, Nigel Shadbolt
Adapting model parameters to incoming streams of data is a crucial factor to deep learning scalability. Interestingly, prior continual learning strategies in online settings inadve…
Interpolating Compressed Parameter Subspaces
Siddhartha Datta, Nigel Shadbolt
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…
Learn2Weight: Parameter Adaptation against Similar-domain Adversarial Attacks
Siddhartha Datta
Recent work in black-box adversarial attacks for NLP systems has attracted much attention. Prior black-box attacks assume that attackers can observe output labels from target model…
Imagining, Studying and Realising A Less Harmful App Ecosystem
Konrad Kollnig, Siddhartha Datta, Nigel Shadbolt
Desktop browser extensions have long allowed users to improve their experience online and tackle widespread harms on websites. So far, no equivalent solution exists for mobile apps…
GreaseVision: Rewriting the Rules of the Interface
Siddhartha Datta, Konrad Kollnig, Nigel Shadbolt
Digital harms can manifest across any interface. Key problems in addressing these harms include the high individuality of harms and the fast-changing nature of digital systems. As…
Low-Loss Subspace Compression for Clean Gains against Multi-Agent Backdoor Attacks
Siddhartha Datta, Nigel Shadbolt
Recent exploration of the multi-agent backdoor attack demonstrated the backfiring effect, a natural defense against backdoor attacks where backdoored inputs are randomly classified…
Mind-proofing Your Phone: Navigating the Digital Minefield with GreaseTerminator
Siddhartha Datta, Konrad Kollnig, Nigel Shadbolt
Digital harms are widespread in the mobile ecosystem. As these devices gain ever more prominence in our daily lives, so too increases the potential for malicious attacks against in…
Backdoors Stuck At The Frontdoor: Multi-Agent Backdoor Attacks That Backfire
Siddhartha Datta, Nigel Shadbolt
Malicious agents in collaborative learning and outsourced data collection threaten the training of clean models. Backdoor attacks, where an attacker poisons a model during training…
Hiding Behind Backdoors: Self-Obfuscation Against Generative Models
Siddhartha Datta, Nigel Shadbolt
Attack vectors that compromise machine learning pipelines in the physical world have been demonstrated in recent research, from perturbations to architectural components. Building…
Widen The Backdoor To Let More Attackers In
Siddhartha Datta, Giulio Lovisotto, Ivan Martinovic +1
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 additiona…
I Want My App That Way: Reclaiming Sovereignty Over Personal Devices
Konrad Kollnig, Siddhartha Datta, Max Van Kleek
Dark patterns in mobile apps take advantage of cognitive biases of end-users and can have detrimental effects on people's lives. Despite growing research in identifying remedies fo…
A study into the impact of anti-extradition bill protests on Bangladeshi immigration into Hong Kong
Siddhartha Datta
Consequences from the 2019 anti-extradition protests in Hong Kong have been studied in many facets, but one topic of interest that has not been explored is the impact on the immigr…
DeepObfusCode: Source Code Obfuscation Through Sequence-to-Sequence Networks
Siddhartha Datta
The paper explores a novel methodology in source code obfuscation through the application of text-based recurrent neural network (RNN) encoder-decoder models in ciphertext generati…