Adversarial ML Problems Are Getting Harder to Solve and to Evaluate
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.
Code (0)
등록된 구현이 없습니다.
Tasks
PositionSimilar Papers 제목 키워드 기반
Learning to Solve Hard Problems in RL for LLMs by Never Giving Up
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
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+1EALG: Evolutionary Adversarial Generation of Language Model-Guided Generators for Combinatorial Optimization
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 ModellingCan LLMs plan paths with extra hints from solvers?
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 SynthesisA Parallel Memory-efficient Epistemic Logic Program Solver: Harder, Better, Faster
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.…