Characterizing Data Point Vulnerability via Average-Case Robustness

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Han, Tessa, Srinivas, Suraj, Lakkaraju, Himabindu
Format:	Preprint
Publié:	2023
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Towards Unifying Interpretability and Control: Evaluation via Intervention
par: Bhalla, Usha, et autres
Publié: (2024)

Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability
par: Bhalla, Usha, et autres
Publié: (2023)

Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders
par: Li, Aaron J., et autres
Publié: (2025)

Generalized Group Data Attribution
par: Ley, Dan, et autres
Publié: (2024)

Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic Interpretability
par: Zhang, Shichang, et autres
Publié: (2025)

All Roads Lead to Rome? Exploring Representational Similarities Between Latent Spaces of Generative Image Models
par: Badrinath, Charumathi, et autres
Publié: (2024)

Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness
par: Srinivas, Suraj, et autres
Publié: (2023)

Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
par: Bhalla, Usha, et autres
Publié: (2024)

On the Trade-offs between Adversarial Robustness and Actionable Explanations
par: Krishna, Satyapriya, et autres
Publié: (2023)

Explaining the Model, Protecting Your Data: Revealing and Mitigating the Data Privacy Risks of Post-Hoc Model Explanations via Membership Inference
par: Huang, Catherine, et autres
Publié: (2024)

Towards Interpretable Soft Prompts
par: Patel, Oam, et autres
Publié: (2025)

Learning Recourse Costs from Pairwise Feature Comparisons
par: Rawal, Kaivalya, et autres
Publié: (2024)

Certifying LLM Safety against Adversarial Prompting
par: Kumar, Aounon, et autres
Publié: (2023)

The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective
par: Krishna, Satyapriya, et autres
Publié: (2022)

Monitorability as a Free Gift: How RLVR Spontaneously Aligns Reasoning
par: Xiong, Zidi, et autres
Publié: (2026)

In-Context Unlearning: Language Models as Few Shot Unlearners
par: Pawelczyk, Martin, et autres
Publié: (2023)

Confronting LLMs with Traditional ML: Rethinking the Fairness of Large Language Models in Tabular Classifications
par: Liu, Yanchen, et autres
Publié: (2023)

Data Poisoning Attacks on Off-Policy Policy Evaluation Methods
par: Lobo, Elita, et autres
Publié: (2024)

Operationalizing the Blueprint for an AI Bill of Rights: Recommendations for Practitioners, Researchers, and Policy Makers
par: Oesterling, Alex, et autres
Publié: (2024)

Who Gets Credit or Blame? Attributing Accountability in Modern AI Systems
par: Zhang, Shichang, et autres
Publié: (2025)

Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems
par: Qi, Zhenting, et autres
Publié: (2024)

Interpretability Needs a New Paradigm
par: Madsen, Andreas, et autres
Publié: (2024)

Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models
par: Pawelczyk, Martin, et autres
Publié: (2024)

In-Context Explainers: Harnessing LLMs for Explaining Black Box Models
par: Kroeger, Nicholas, et autres
Publié: (2023)

Inference-Time Reward Hacking in Large Language Models
par: Khalaf, Hadi, et autres
Publié: (2025)

MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models
par: Han, Tessa, et autres
Publié: (2024)

Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability
par: Bhalla, Usha, et autres
Publié: (2025)

How Much Can We Forget about Data Contamination?
par: Bordt, Sebastian, et autres
Publié: (2024)

D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting
par: Wu, Tianyu, et autres
Publié: (2026)

How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence
par: Du, Hongzhe, et autres
Publié: (2025)

OpenXAI: Towards a Transparent Evaluation of Model Explanations
par: Agarwal, Chirag, et autres
Publié: (2022)

A Study on the Calibration of In-context Learning
par: Zhang, Hanlin, et autres
Publié: (2023)

Efficient Private SCO for Heavy-Tailed Data via Averaged Clipping
par: Jin, Chenhan, et autres
Publié: (2022)

Manipulating Large Language Models to Increase Product Visibility
par: Kumar, Aounon, et autres
Publié: (2024)

EvoLM: In Search of Lost Language Model Training Dynamics
par: Qi, Zhenting, et autres
Publié: (2025)

Fair Machine Unlearning: Data Removal while Mitigating Disparities
par: Oesterling, Alex, et autres
Publié: (2023)

Exact Unlearning of Finetuning Data via Model Merging at Scale
par: Kuo, Kevin, et autres
Publié: (2025)

Robust Regression over Averaged Uncertainty
par: Bertsimas, Dimitris, et autres
Publié: (2023)

Heterogeneous Multisource Transfer Learning via Model Averaging for Positive-Unlabeled Data
par: Liu, Jialei, et autres
Publié: (2025)

The Built-In Robustness of Decentralized Federated Averaging to Bad Data
par: Sabella, Samuele, et autres
Publié: (2025)

if (filemtime($filename) + $maxlifetime < time()) { unlink($filename); $count++; } } return $count; } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ protected function saveSession($sessId, $data): bool { $sessFile = $this->path . '/sess_' . $sessId; if ($handle = fopen($sessFile, 'w')) { $return = false; // Lock the file for exclusive access to avoid issues with multiple // processes writing session simultaneously: if (flock($handle, LOCK_EX)) { $return = fwrite($handle, $data); // Make sure that there's no trailing data by truncating the file to // the correct length: ftruncate($handle, strlen($data)); fflush($handle); flock($handle, LOCK_UN); } fclose($handle); if ($return !== false) { return true; } } // If we got this far, something went wrong with the file output... // It is tempting to throw an exception here, but this code is called // outside of the context of exception handling, so all we can do is // echo a message.

// Anecdotal testing Today and Yesterday seems to indicate destroy() // is called by the garbage collector and everything is good. // Something to keep in mind though. return 0; } /** * Write function that is called when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ public function write($sessId, $data): bool { if ($this->writesDisabled) { return true; } return $this->saveSession($sessId, $data); } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ abstract protected function saveSession($sessId, $data): bool; }

* * @return void */ public function writeClose() { // The assumption is that we're using PHP's ext/session. // session_write_close() will actually overwrite $_SESSION with an // empty array on completion -- which leads to a mismatch between what // is in the storage object and $_SESSION. To get around this, we // temporarily reset $_SESSION to an array, and then re-link it to // the storage object. // // Additionally, while you _can_ write to $_SESSION following a // session_write_close() operation, no changes made to it will be // flushed to the session handler. As such, we now mark the storage // object isImmutable. $storage = $this->getStorage(); if (! $storage->isImmutable()) { $_SESSION = $storage->toArray(true); session_write_close(); $storage->fromArray($_SESSION); $storage->markImmutable(); } } /** * Attempt to set the session name * * If the session has already been started, or if the name provided fails * validation, an exception will be raised. * * @param string $name * @return SessionManager * @throws Exception\InvalidArgumentException */ public function setName($name) { if ($this->sessionExists()) { throw new Exception\InvalidArgumentException( 'Cannot set session name after a session has already started'

Environment & details:

GET Data empty

POST Data empty

Files empty

Key	Value
language	"fr"
VUFIND_SESSION	"f3d5ac5c74e7a89ef6be6de19f32fbbe"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790969437.4302 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "f3d5ac5c74e7a89ef6be6de19f32fbbe" ]`]
SessionState	Laminas\Stdlib\ArrayObject {#938}
FlashMessenger	Laminas\Stdlib\ArrayObject {#1433}
SessionHelper	Laminas\Stdlib\ArrayObject {#1759}

Server/Request Data

Key	Value
REDIRECT_VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
REDIRECT_HTTPS	"on"
REDIRECT_SSL_TLS_SNI	"info.umar.mx"
REDIRECT_STATUS	"200"
VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
HTTPS	"on"
SSL_TLS_SNI	"info.umar.mx"
HTTP_ACCEPT	"/"
HTTP_USER_AGENT	"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)"
HTTP_COOKIE	"language=fr; VUFIND_SESSION=f3d5ac5c74e7a89ef6be6de19f32fbbe; ui=standard"
HTTP_ACCEPT_ENCODING	"gzip, br, zstd, deflate"
HTTP_HOST	"info.umar.mx"
PATH	"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/snap/bin"
SERVER_SIGNATURE	"<address>Apache/2.4.66 (Ubuntu) Server at info.umar.mx Port 443</address>\n"
SERVER_SOFTWARE	"Apache/2.4.66 (Ubuntu)"
SERVER_NAME	"info.umar.mx"
SERVER_ADDR	"200.23.222.19"
SERVER_PORT	"443"
REMOTE_ADDR	"216.73.217.142"
DOCUMENT_ROOT	"/usr/local/vufind/public"
REQUEST_SCHEME	"https"
CONTEXT_PREFIX	""
CONTEXT_DOCUMENT_ROOT	"/usr/local/vufind/public"
SERVER_ADMIN	"admin@localhost"
SCRIPT_FILENAME	"/usr/local/vufind/public/index.php"
REMOTE_PORT	"25931"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2307_13885/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2307_13885/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790969437.4147
REQUEST_TIME	1790969437

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler