paper-with-me

홈 › Papers

Adversarial ML Problems Are Getting Harder to Solve and to Evaluate

2025-02-04 · Javier Rando, Jie Zhang, Nicholas Carlini, Florian Tramèr

In the past decade, considerable research effort has been devoted to securing machine learning (ML) models that operate in adversarial settings. Yet, progress has been slow even for simple "toy" problems (e.g., robustness to small adversarial perturbations) and is often hindered by non-rigorous evaluations. Today, adversarial ML research has shifted towards studying larger, general-purpose language models. In this position paper, we argue that the situation is now even worse: in the era of LLMs, the field of adversarial ML studies problems that are (1) less clearly defined, (2) harder to solve, and (3) even more challenging to evaluate. As a result, we caution that yet another decade of work on adversarial ML may fail to produce meaningful progress.

📄 PDF Abstract BibTeX arXiv:2502.02260

Code (0)

등록된 구현이 없습니다.

Tasks

Position

Similar Papers 제목 키워드 기반

Learning to Solve Hard Problems in RL for LLMs by Never Giving Up

2026-09-11 · Michael Noukhovitch, Hamish Ivison, Nathan Lambert, Aaron Courville hf

We demonstrate that training LLMs with RL does not improve performance equally across a dataset. RL shows large improvements on easy problems that an LLM is already good at solving, but small improvements on hard problem…

Adversarial Attacks on Face Detectors using Neural Net based Constrained Optimization

2018-05-31 · Avishek Joey Bose, Parham Aarabi

Adversarial attacks involve adding, small, often imperceptible, perturbations to inputs with the goal of getting a machine learning model to misclassifying them. While many different adversarial attack strategies have be…

Adversarial Attackimage-classificationImage Classificationobject-detection+1

EALG: Evolutionary Adversarial Generation of Language Model-Guided Generators for Combinatorial Optimization

2025-06-03 · Ruibo Duan, Yuxin Liu, Xinyao Dong, Chenglin Fan

Generating challenging instances is crucial for the evaluation and advancement of combinatorial optimization solvers. In this work, we introduce EALG (Evolutionary Adversarial Generation of Language Model-Guided Generato…

Combinatorial OptimizationLanguage ModelingLanguage Modelling

Can LLMs plan paths with extra hints from solvers?

2024-10-07 · Erik Wu, Sayan Mitra

Large Language Models (LLMs) have shown remarkable capabilities in natural language processing, mathematical problem solving, and tasks related to program synthesis. However, their effectiveness in long-term planning and…

Mathematical Problem-SolvingProgram Synthesis

A Parallel Memory-efficient Epistemic Logic Program Solver: Harder, Better, Faster

2016-08-24 · Patrick Thor Kahl, Anthony P. Leclerc, Tran Cao Son

As the practical use of answer set programming (ASP) has grown with the development of efficient solvers, we expect a growing interest in extensions of ASP as their semantics stabilize and solvers supporting them mature.…