Open Problems

Machine Unlearning

Benchmarking the Adversarial Robustness and Reversibility of LLM Unlearning

Effect to explainPartly addressed
Possible candidate · 2/5 runs6 papers report this83% from 2025+

Generated automatically from the limitations stated in 6 papers (ICLR, ICML, NAACL), listed under Evidence. It is not a paper, and it does not come from papers submitted to CSPaper.

The problem

Existing LLM unlearning methods are predominantly evaluated on standard, benign queries, giving a false sense of compliance with privacy and copyright demands. Empirical evidence shows that "unlearned" knowledge remains extractable via adversarial jailbreaks, latent-space elicitation, and few-shot relearning. Without systematic evaluation across these extraction vectors, practitioners have no way to verify whether a model has actually eliminated sensitive data or merely applied a superficial suppression mask.

Why it matters

Enables researchers and auditors to quantitatively verify whether an unlearning method provides persistent knowledge erasure or fragile behavioral suppression. It establishes the first standardized evaluation protocol for unlearning irreversibility under adversarial and relearning conditions.

Ways to approach it

Prior-work checks are free with an account. Results someone already ran are shown to everyone.

  1. 1

    Unified Extraction Benchmark: Build an evaluation harness that subjects top unlearning methods (e.g., gradient ascent, preference optimization, weight localization) to standardized red-teaming: diverse jailbreak templates, white-box activation probing, and low-budget relearning (varying sample count $M \in [1, 50]$ and epochs). Measure knowledge extraction rate and relearning speedup relative to a blank-slate model.

  2. 2

    Relearning-Resistant Objectives: Formulate unlearning objectives that optimize against relearning dynamics—such as regularizing the Fisher information along forget directions or projecting weight updates orthogonal to forget-related parameter submanifolds. Measure post-relearning retention of target knowledge versus standard task utility.

Have a different approach?

Describe how you would tackle this problem and we'll look for papers that already do it. Free; your text stays private.

Free · 3 checks per day

Why it might fail

If concurrent benchmark efforts rapidly standardize unlearning robustness evaluations, diminishing the novelty of purely empirical auditing, or if fundamental information-theoretic bounds prove that robust unlearning in overparameterized networks strictly requires full dataset retraining.

Evidence

Each paper's own statement of the limitation, verbatim.

Nearest existing work

Related open problems

Machine Unlearning

Scope to testOpen

A Standardized Multi-Architecture Testbed of Memorized Concepts, Generation Fingerprints, and Editable Structures in Text-to-Image Models Beyond Stable Diffusion v1.x

Nearly every quantitative claim about text-to-image models — memorization, unlearning success, watermark robustness, deepfake provenance, concept editability — is anchored to a handful of frozen Stable Diffusion v1.x/v2 checkpoints, because those are the only models with established benchmarks, known memorized prompts, and validated concept labels. Newer architectures (DiT-based diffusion, DeepFloyd, autoregressive and GAN generators, video models) are largely untested, so results that appear robust may be artifacts of one 2022 model family. The field cannot tell whether its findings are properties of generative modeling or properties of Stable Diffusion 1.4.

Strong candidate · 5/5 runs22 papers report this88% from 2025+

Machine Unlearning

Effect to explainPartly addressed

Empirical Robustness and Sensitivity of Machine Unlearning Under Realistic Data and Checkpoint Constraints

Existing machine unlearning algorithms for language models are predominantly evaluated under idealized conditions: complete access to forget sets, clean entity anchors, standard prose, and checkpoints saved immediately before target data exposure. In practice, unlearning requests frequently present partial forget data, domain variations like code, noisy or alias-heavy entity mentions, and checkpoints separated from target exposure by billions or trillions of tokens. Practitioners currently cannot predict whether an unlearning method that succeeds on curated benchmarks like TOFU will retain any efficacy when deployed under these real-world data and provenance constraints.

Strong candidate · 1/1 runs4 papers report this50% from 2025+

Machine Unlearning

Barrier to removePartly addressed

Machine Unlearning Under Degraded Operational Preconditions

Existing machine unlearning methods rely on strict operational preconditions: access to clean retain datasets ($D_r$), full white-box parameter access, historical pre-training checkpoints, or original pre-unlearned calibration weights. In production environments, intermediate training checkpoints are routinely deleted to save storage, retain data is often inaccessible due to data governance policies, and deployment interfaces may restrict full weight access. Without methods that function in the absence of these preconditions, deployed models cannot legally or practically comply with data deletion requests.

Possible candidate · 2/5 runs4 papers report this75% from 2025+

Machine Unlearning

Effect to explainOpen

Scalability and Robustness of Machine Unlearning Under Varying Forget-Set Regimes

Existing machine unlearning techniques are only validated in narrow operating windows, typically limited to small forget budgets ($\le 10\%$). As forget sets scale beyond a few hundred samples or exceed 10–20% of the training distribution, retention accuracy drops significantly (e.g., a 14–15% gap relative to retraining from scratch on CIFAR-10), while tiny splits (e.g., 1%) yield negligible unlearning. Furthermore, unlearned representations remain fragile and easily recoverable when exposed to small fractions of the forgotten data during relearning. Consequently, current unlearning algorithms cannot be reliably deployed for large-scale data deletion compliance without catastrophic utility loss.

Possible candidate · 2/5 runs4 papers report this100% from 2025+
Generated automatically, not curated by hand. Automated prior-work checks catch about a third of existing work, so treat this problem as a lead to investigate.