Adversarial　attack　is　a　crucial　step　when　evaluating　the　reliability　and　robustness　of　deep　neural　networks　(DNNs)　models.　Most　existing　attack　approaches　apply　an　end-to-end　gradient　update　strategy　to　generate　adversarial　examples　for　a　classification　or　regression　problem.　However,　few　of　them　consider　the　non-differentiable　DNN　models　(e.g.,　coordinate　regression　model)　that　prevent　end-to-end　backpropagation　resulting　in　the　failure　of　gradient　calculation.　In　this　article,　we　present　a　new　adversarial　example　generation　approach　for　both　untargeted　and　targeted　attacks　on　coordinate　regression　models　with　non-differentiable　operations.　The　novelty　of　our　approach　lies　in　a　kk-layer　penetrating　representation,　on　which　we　perturb　the　hidden　feature　distribution　of　the　kkth　layer　through　relational　guidance　to　influence　the　final　output,　in　which　end-to-end　backpropagation　is　not　required.　Rather　than　modifying　a　large　portion　of　the　pixels　in　an　image,　the　proposed　approach　only　modifies　a　very　small　set　of　the　input　pixels.　These　pixels　are　carefully　and　precisely　selected　by　three　correlations　between　the　input　pixels　and　hidden　features　of　the　kkth　layer　of　a　DNN,　thus　significantly　reducing　the　adversarial　perturbation　on　a　clean　image.　We　successfully　apply　the　proposed　approach　to　two　different　tasks　(i.e.,　2D　and　3D　human　pose　estimation)　which　are　typical　applications　of　the　coordinate　regression　learning.　The　comprehensive　experiments　demonstrate　that　our　approach　achieves　better　performance　while　using　much　less　adversarial　perturbation　on　clean　images.　©　2004-2012　IEEE.