arXiv subjects

Amartya Sanyal

Publications and source records attributed to Amartya Sanyal.

At least 19 recordsLinked to original sources

arXiv2026

Why Forget-Only Unlearning Needs Memorization

Machine unlearning asks for a deletion algorithm whose output is close to retraining from scratch without the selected forget examples. In this work, we study forget-only unlearning, where the deletion algorithm receives only the trained model and the examples to forget, with no retained data or extra training information. We ask whether forget-only unlearning is always possible. We first show that this depends on the learning method: different datasets can produce the same trained model but require very different outputs after the same examples are removed. Using this observation, we derive lower bounds on how accurately unlearning can match retraining and instantiate them for several standard learning algorithms. We then ask what must be true when forget-only unlearning succeeds. To this end, we derive lower bounds on what an algorithm must memorize about the training data to handle arbitrary deletion requests. For simple threshold learners, the required information can be as large as the entire dataset, even though ordinary training keeps only one boundary point. Overall, our results show that information discarded during ordinary learning may be needed later for deletion, so models designed for forget-only unlearning may need to retain more information than standard training does.

cs.LG↗

arXiv2026

Private online learning and prediction for Littlestone classes

We study mistake bounds for differentially private online learning and online prediction under oblivious realisable adversaries. Online learning requires the learner to release a hypothesis at each time step whereas in online prediction, the learner only needs to make predictions without releasing a hypothesis. Using a novel lower bound for private online learning and an upper bound for private prediction, we show that the sample complexity of these two problems are separated by a factor that grows with the time horizon for every class of finite Littlestone dimension $d$. First, we prove that every $(ε,δ)$-private online learner has a deterministic realisable stream of length $T$ on which the mistake bound is at least $\mathbb E [M_T]= O\left(\frac dε\log^{2/3} T\right)$. In particular, this is the first non-trivial lower in the range $1/T<δ<1/\log T)$ left open in earlier works[SR22,DSS24,LWY24]. Second, we prove that for every class of of Littlestone dimension $d$, there exists an $(ε,δ)$-jointly private predictor with at most $2^{2^{cd^2}}ε^{-2}\log^2(2/(εδ))$ expected mistakes, independently of $T$, for some absolute constant $c>0$. Thus, for every fixed class of finite Littlestone dimension when $δ=Θ(1/\log T)$, private learning requires $O\left(\log^{2/3} T\right)$ expected mistakes, whereas private prediction admits $O(\log\log T^2)$.

cs.LG↗

arXiv2026

Minority Collective Action for User-Side Fairness

Machine learning models often preserve biases present in training data, leading to unfair treatment of certain minority groups. Despite an array of existing firm-side bias mitigation techniques, they typically incur utility costs and require organizational buy-in. Recognizing that many models rely on user-contributed data, end-users can induce fairness through the framework of Algorithmic Collective Action, where a coordinated minority group strategically relabels its own data to enhance fairness, without altering the firm's training process. We propose three practical, model-agnostic methods to approximate ideal relabeling and validate them on real-world datasets. Our findings show that a subgroup of the minority can substantially reduce unfairness with a small impact on the overall prediction error.

cs.LG↗

arXiv2026

Language Generation with Replay: A Learning-Theoretic View of Model Collapse

As scaling laws push the training of frontier large language models (LLMs) toward ever-growing data requirements, training pipelines are approaching a regime where much of the publicly available online text may be consumed. At the same time, widespread LLM usage increases the volume of machine-generated content on the web; together, these trends raise the likelihood of generated text re-entering future training corpora, increasing the associated risk of performance degradation often called model collapse. In practice, model developers address this concern through data cleaning, watermarking, synthetic-data policies, or, in some cases, blissful ignorance. However, the problem of model collapse in generative models has not been examined from a learning-theoretic perspective: we study it through the theoretical lens of the language generation in the limit framework, introducing a replay adversary that augments the example stream with the generator's own past outputs. Our main contribution is a fine-grained learning-theoretic characterization of when replay fundamentally limits generation: while replay is benign for the strongest notion of uniform generation, it provably creates separations for the weaker notions of non-uniform generation and generation in the limit. Interestingly, our positive results mirror heuristics widely used in practice, such as data cleaning, watermarking, and output filtering, while our separations show when these ideas can fail.

cs.LG↗

arXiv2026

Adaptive Sampling and Clipping for Private Worst-Case Group Optimization

A central requirement for the acceptance of machine learning methods for human-centric tasks is that they should be fair, in the sense that they should work comparably well for individuals from different societal groups. A second, equally important, requirement is that they should respect the privacy of user data. While techniques exist to address each aspect in isolation, such as worst-case group optimization for the former and differentially private SGD for the latter, these are often at odds with with each other, and no practical method currently exists to enforce both requirements simultaneously. In this work, we overcome this problem and propose an algorithm for optimizing the worst-case group accuracy in a differentially private way. Our main contribution is ASC (Adaptively Sampled and Clipped Worst-case Group Optimization), which adaptively controls both the sampling rate and the clipping threshold of each group's gradient contributions. Thereby, it is able to reweight the training objective in favor of harder-to-learn groups, while keeping the noise required to enforce privacy low enough to preserve model utility. Our experiments show that ASC achieves substantially higher worst-case group accuracy than prior work, without sacrificing overall average accuracy.

cs.LG↗

arXiv2026

Less Noise, Same Certificate: Retain Sensitivity for Unlearning

Certified machine unlearning aims to provably remove the influence of a deletion set $U$ from a model trained on a dataset $S$, by producing an unlearned output that is statistically indistinguishable from retraining on the retain set $R:=S\setminus U$. Many existing certified unlearning methods adapt techniques from Differential Privacy (DP) and add noise calibrated to global sensitivity, i.e., the worst-case output change over all adjacent datasets. We show that this DP-style calibration is often overly conservative for unlearning, based on a key observation: certified unlearning, by definition, does not require protecting the privacy of the retained data $R$. Motivated by this distinction, we define retain sensitivity as the worst-case output change over deletions $U$ while keeping $R$ fixed. While insufficient for DP, retain sensitivity is exactly sufficient for unlearning, allowing for the same certificates with less noise. We validate these reductions in noise theoretically and empirically across several problems, including the weight of minimum spanning trees, PCA, and ERM. Finally, we refine the analysis of two widely used certified unlearning algorithms through the lens of retain sensitivity, leveraging the regularity induced by $R$ to further reduce noise and improve utility.

cs.LG↗

arXiv2026

LoRA and Privacy: When Random Projections Help (and When They Don't)

We introduce the (Wishart) projection mechanism, a randomized map of the form $S \mapsto M f(S)$ with $M \sim W_d(1/r I_d, r)$ and study its differential privacy properties. For vector-valued queries $f$, we prove non-asymptotic DP guarantees without any additive noise, showing that Wishart randomness alone can suffice. For matrix-valued queries, however, we establish a sharp negative result: in the noise-free setting, the mechanism is not DP, and we demonstrate its vulnerability by implementing a near perfect membership inference attack (AUC $> 0.99$). We then analyze a noisy variant and prove privacy amplification due to randomness and low rank projection, in both large- and small-rank regimes, yielding stronger privacy guarantees than additive noise alone. Finally, we show that LoRA-style updates are an instance of the matrix-valued mechanism, implying that LoRA is not inherently private despite its built-in randomness, but that low-rank fine-tuning can be more private than full fine-tuning at the same noise level. Preliminary experiments suggest that tighter accounting enables lower noise and improved accuracy in practice.

cs.LG↗

arXiv2025

Delta-Influence: Unlearning Poisons via Influence Functions

Addressing data integrity challenges, such as unlearning the effects of data poisoning after model training, is necessary for the reliable deployment of machine learning models. State-of-the-art influence functions, such as EK-FAC and TRAK, often fail to accurately attribute abnormal model behavior to the specific poisoned training data responsible for the data poisoning attack. In addition, traditional unlearning algorithms often struggle to effectively remove the influence of poisoned samples, particularly when only a few affected examples can be identified. To address these challenge, we introduce $Δ$-Influence, a novel approach that leverages influence functions to trace abnormal model behavior back to the responsible poisoned training data using as little as just one poisoned test example. $Δ$-Influence applies data transformations that sever the link between poisoned training data and compromised test points without significantly affecting clean data. This allows $Δ$-Influence to detect large negative shifts in influence scores following data transformations, a phenomenon we term as influence collapse, thereby accurately identifying poisoned training data. Unlearning this subset, e.g. through retraining, effectively eliminates the data poisoning. We validate our method across three vision-based poisoning attacks and three datasets, benchmarking against five detection algorithms and five unlearning strategies. We show that $Δ$-Influence consistently achieves the best unlearning across all settings, showing the promise of influence functions for corrective unlearning. Our code is publicly available at: https://github.com/Ruby-a07/delta-influence

cs.CV↗

arXiv2025

Learning in an Echo Chamber: Online Learning with Replay Adversary

As machine learning systems increasingly train on self-annotated data, they risk reinforcing errors and becoming echo chambers of their own beliefs. We model this phenomenon by introducing a learning-theoretic framework: Online Learning in the Replay Setting. In round $t$, the learner outputs a hypothesis $\hat{h}_t$; the adversary then reveals either the true label $f^\ast(x_t)$ or a replayed label $\hat{h}_i(x_t)$ from an earlier round $i < t$. A mistake is counted only when the true label is shown, yet classical algorithms such as the SOA or the halving algorithm are easily misled by the replayed errors. We introduce the Extended Threshold dimension, $\mathrm{ExThD}(\mathcal{H})$, and prove matching upper and lower bounds that make $\mathrm{ExThD}(\mathcal{H})$ the exact measure of learnability in this model. A closure-based learner makes at most $\mathrm{ExThD}(\mathcal{H})$ mistakes against any adaptive adversary, and no algorithm can perform better. For stochastic adversaries, we prove a similar bound for every intersection-closed class. The replay setting is provably harder than the classical mistake bound setting: some classes have constant Littlestone dimension but arbitrarily large $\mathrm{ExThD}(\mathcal{H})$. Proper learning exhibits an even sharper separation: a class is properly learnable under replay if and only if it is (almost) intersection-closed. Otherwise, every proper learner suffers $Ω(T)$ errors, whereas our improper algorithm still achieves the $\mathrm{ExThD}(\mathcal{H})$ bound. These results give the first tight analysis of learning against replay adversaries, based on new results for closure-type algorithms.

cs.LG↗

arXiv2025

An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise

Given $n$ i.i.d. random matrices $A_i \in \mathbb{R}^{d \times d}$ that share a common expectation $Σ$, the objective of Differentially Private Stochastic PCA is to identify a subspace of dimension $k$ that captures the largest variance directions of $Σ$, while preserving differential privacy (DP) of each individual $A_i$. Existing methods either (i) require the sample size $n$ to scale super-linearly with dimension $d$, even under Gaussian assumptions on the $A_i$, or (ii) introduce excessive noise for DP even when the intrinsic randomness within $A_i$ is small. Liu et al. (2022a) addressed these issues for sub-Gaussian data but only for estimating the top eigenvector ($k=1$) using their algorithm DP-PCA. We propose the first algorithm capable of estimating the top $k$ eigenvectors for arbitrary $k \leq d$, whilst overcoming both limitations above. For $k=1$ our algorithm matches the utility guarantees of DP-PCA, achieving near-optimal statistical error even when $n = \tilde{\!O}(d)$. We further provide a lower bound for general $k > 1$, matching our upper bound up to a factor of $k$, and experimentally demonstrate the advantages of our algorithm over comparable baselines.

stat.ML↗

arXiv2025

Online Learning and Unlearning

We formalize the problem of online learning-unlearning, where a model is updated sequentially in an online setting while accommodating unlearning requests between updates. After a data point is unlearned, all subsequent outputs must be statistically indistinguishable from those of a model trained without that point. We present two online learner-unlearner (OLU) algorithms, both built upon online gradient descent (OGD). The first, passive OLU, leverages OGD's contractive property and injects noise when unlearning occurs, incurring no additional computation. The second, active OLU, uses an offline unlearning algorithm that shifts the model toward a solution excluding the deleted data. Under standard convexity and smoothness assumptions, both methods achieve regret bounds comparable to those of standard OGD, demonstrating that one can maintain competitive regret bounds while providing unlearning guarantees.

cs.LG↗

arXiv2025

Provable unlearning in topic modeling and downstream tasks

Machine unlearning algorithms are increasingly important as legal concerns arise around the provenance of training data, but verifying the success of unlearning is often difficult. Provable guarantees for unlearning are often limited to supervised learning settings. In this paper, we provide the first theoretical guarantees for unlearning in the pre-training and fine-tuning paradigm by studying topic models, simple bag-of-words language models that can be adapted to solve downstream tasks like retrieval and classification. First, we design a provably effective unlearning algorithm for topic models that incurs a computational overhead independent of the size of the original dataset. Our analysis additionally quantifies the deletion capacity of the model -- i.e., the number of examples that can be unlearned without incurring a significant cost in model performance. Finally, we formally extend our analyses to account for adaptation to a given downstream task. In particular, we design an efficient algorithm to perform unlearning after fine-tuning the topic model via a linear head. Notably, we show that it is easier to unlearn pre-training data from models that have been fine-tuned to a particular task, and one can unlearn this data without modifying the base model.

cs.LG↗

arXiv2025

Differentially Private Steering for Large Language Model Alignment

Aligning Large Language Models (LLMs) with human values and away from undesirable behaviors (such as hallucination) has become increasingly important. Recently, steering LLMs towards a desired behavior via activation editing has emerged as an effective method to mitigate harmful generations at inference-time. Activation editing modifies LLM representations by preserving information from positive demonstrations (e.g., truthful) and minimising information from negative demonstrations (e.g., hallucinations). When these demonstrations come from a private dataset, the aligned LLM may leak private information contained in those private samples. In this work, we present the first study of aligning LLM behavior with private datasets. Our work proposes the Private Steering for LLM Alignment (PSA) algorithm to edit LLM activations with differential privacy (DP) guarantees. We conduct extensive experiments on seven different benchmarks with open-source LLMs of different sizes (0.5B to 7B) and model families (LlaMa, Qwen, Mistral and Gemma). Our results show that PSA achieves DP guarantees for LLM alignment with minimal loss in performance, including alignment metrics, open-ended text generation quality, and general-purpose reasoning. We also develop the first Membership Inference Attack (MIA) for evaluating and auditing the empirical privacy for the problem of LLM steering via activation editing. Our experiments support the theoretical guarantees by showing improved guarantees for our PSA algorithm compared to several existing non-private techniques.

cs.CL↗

arXiv2025

Open Problems in Machine Unlearning for AI Safety

As AI systems become more capable, widely deployed, and increasingly autonomous in critical areas such as cybersecurity, biological research, and healthcare, ensuring their safety and alignment with human values is paramount. Machine unlearning -- the ability to selectively forget or suppress specific types of knowledge -- has shown promise for privacy and data removal tasks, which has been the primary focus of existing research. More recently, its potential application to AI safety has gained attention. In this paper, we identify key limitations that prevent unlearning from serving as a comprehensive solution for AI safety, particularly in managing dual-use knowledge in sensitive domains like cybersecurity and chemical, biological, radiological, and nuclear (CBRN) safety. In these contexts, information can be both beneficial and harmful, and models may combine seemingly harmless information for harmful purposes -- unlearning this information could strongly affect beneficial uses. We provide an overview of inherent constraints and open problems, including the broader side effects of unlearning dangerous knowledge, as well as previously unexplored tensions between unlearning and existing safety mechanisms. Finally, we investigate challenges related to evaluation, robustness, and the preservation of safety features during unlearning. By mapping these limitations and open challenges, we aim to guide future research toward realistic applications of unlearning within a broader AI safety framework, acknowledging its limitations and highlighting areas where alternative approaches may be required.

cs.LG↗

arXiv2024

On the Growth of Mistakes in Differentially Private Online Learning: A Lower Bound Perspective

In this paper, we provide lower bounds for Differentially Private (DP) Online Learning algorithms. Our result shows that, for a broad class of $(\varepsilon,δ)$-DP online algorithms, for number of rounds $T$ such that $\log T\leq O(1 / δ)$, the expected number of mistakes incurred by the algorithm grows as $Ω(\log \frac{T}δ)$. This matches the upper bound obtained by Golowich and Livni (2021) and is in contrast to non-private online learning where the number of mistakes is independent of $T$. To the best of our knowledge, our work is the first result towards settling lower bounds for DP-Online learning and partially addresses the open question in Sanyal and Ramponi (2022).

cs.LG↗

arXiv2024

Corrective Machine Unlearning

Machine Learning models increasingly face data integrity challenges due to the use of large-scale training datasets drawn from the Internet. We study what model developers can do if they detect that some data was manipulated or incorrect. Such manipulated data can cause adverse effects including vulnerability to backdoored samples, systemic biases, and reduced accuracy on certain input domains. Realistically, all manipulated training samples cannot be identified, and only a small, representative subset of the affected data can be flagged. We formalize Corrective Machine Unlearning as the problem of mitigating the impact of data affected by unknown manipulations on a trained model, only having identified a subset of the corrupted data. We demonstrate that the problem of corrective unlearning has significantly different requirements from traditional privacy-oriented unlearning. We find most existing unlearning methods, including retraining-from-scratch without the deletion set, require most of the manipulated data to be identified for effective corrective unlearning. However, one approach, Selective Synaptic Dampening, achieves limited success, unlearning adverse effects with just a small portion of the manipulated samples in our setting, which shows encouraging signs for future progress. We hope our work spurs research towards developing better methods for corrective unlearning and offers practitioners a new strategy to handle data integrity challenges arising from web-scale training. Code is available at https://github.com/drimpossible/corrective-unlearning-bench.

cs.LG↗

arXiv2024

Protecting against simultaneous data poisoning attacks

Current backdoor defense methods are evaluated against a single attack at a time. This is unrealistic, as powerful machine learning systems are trained on large datasets scraped from the internet, which may be attacked multiple times by one or more attackers. We demonstrate that simultaneously executed data poisoning attacks can effectively install multiple backdoors in a single model without substantially degrading clean accuracy. Furthermore, we show that existing backdoor defense methods do not effectively prevent attacks in this setting. Finally, we leverage insights into the nature of backdoor attacks to develop a new defense, BaDLoss, that is effective in the multi-attack setting. With minimal clean accuracy degradation, BaDLoss attains an average attack success rate in the multi-attack setting of 7.98% in CIFAR-10 and 10.29% in GTSRB, compared to the average of other defenses at 64.48% and 84.28% respectively.

cs.LG↗

arXiv2024

What Makes and Breaks Safety Fine-tuning? A Mechanistic Study

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation framework that captures salient aspects of an unsafe input by modeling the interaction between the task the model is asked to perform (e.g., "design") versus the specific concepts the task is asked to be performed upon (e.g., a "cycle" vs. a "bomb"). Using this, we investigate three well-known safety fine-tuning methods -- supervised safety fine-tuning, direct preference optimization, and unlearning -- and provide significant evidence demonstrating that these methods minimally transform MLP weights to specifically align unsafe inputs into its weights' null space. This yields a clustering of inputs based on whether the model deems them safe or not. Correspondingly, when an adversarial input (e.g., a jailbreak) is provided, its activations are closer to safer samples, leading to the model processing such an input as if it were safe. We validate our findings, wherever possible, on real-world models -- specifically, Llama-2 7B and Llama-3 8B.

cs.LG↗