Programming-by-example systems infer programs from a small set of input-output examples. Robust PBE work usually models wrong examples as samples from a stochastic noise process and then minimizes an expected or empirical loss. This paper studies a different failure mode: an adversary who sees the synthesizer and chooses the examples whose corruption most damages the returned program. We formalize fixed-set worst-case corruption for finite PBE version spaces, implement exact-within-bounded-pool and heuristic corruption searches for a string-transformation DSL, and introduce version-space partition aggregation (VPA), a defense that synthesizes on disjoint example groups and votes by semantic signatures. The central claim is deliberately bounded and partly negative: low-margin PBE tasks have an adversarial robustness dimension that random-typo and noisy-PBE evaluations miss, while semantic partition aggregation helps only when the clean semantics keep a partition vote margin, which often fails on realistic tasks. Evidence from curated/generated DSL tasks, accepted public SyGuS PBE_SLIA slices, SYNTRA Playgol v2, and noisy-PBE objective baselines supports that boundary. One curated edit flips all 8 spike tasks while 200-trial typo, DSL-pool, and distance-matched random controls succeed on 10.3%, 11.0%, and 16.7%; generated margin-1 rows flip under budget 1 yet VPA recovers them; on public SyGuS the vote margin is near one, so an adaptive attacker drives VPA accuracy to zero; accepted public SyGuS slices move across exact-within-pool budget boundaries; and Playgol shows positive paired-bootstrap gaps against typo and same-pool random controls on the 141 accepted rows. A small exact-output prompt harness over 20 controlled margin-1 tasks shows the same qualitative clean-to-attacked pattern across local and API models, while it is treated as a scope check, not a broad LLM benchmark.
Low Rank Matrix Recovery with Simultaneous Presence of Outliers and Sparse Corruption
University of Central Florida(中佛罗里达大学)
本文研究了一个数据模型,其中数据矩阵D可以表示为D = L + S + C,其中L是低秩矩阵,S是元素稀疏矩阵,C是非零列为离群数据点的矩阵。到目前为止,强大的PCA算法只考虑S或C的模型,而不是两者都考虑。因此,现有的算法不能同时考虑元素和列的腐败。本文提出了一种新的鲁棒PCA算法,该算法对同时发生的腐败类型具有鲁棒性。我们的方法依赖于稀疏损坏列的稀疏近似,使得列相对于其他数据点的稀疏扩展用于区分稀疏损坏的内点列和外围数据点。我们还开发了一个随机设计,提供了一个可扩展的实施所提出的方法。稀疏近似的核心思想进行了分析,我们表明,潜在的ell_1-范数最小化可以获得一个内点的稀疏腐败的存在下的表示。
Robustness to Sparse Adversarial Corruption in Arbitrary Linear Measurements: Beyond Exact Recovery
IMT Atlantique, Lab-STICC, CNRS UMR 6285(IMT Atlantique,Lab-STICC,CNRS UMR 6285);Department of Computer Science and Automation, Indian Institute of Science(计算机科学与自动化系,印度科学研究院)
ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning
Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院,清华大学);The Chinese University of Hong Kong(香港中文大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学深圳分校);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)