Deep-learning based classification algorithms have been shown to be susceptible to adversarial attacks: minor changes to the input of classifiers can dramatically change their outputs, while being imperceptible to humans. In this paper, we present a simple hypothesis about a feature compression property of artificial i…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “classifier fragility”
In order for machine learning to be deployed and trusted in many applications, it is crucial to be able to reliably explain why the machine learning algorithm makes certain predictions. For example, if an algorithm classifies a given pathology image to be a malignant tumor, then the doctor may need to know which parts …
FaceSigns embeds a secret watermark in images to authenticate and detect deepfakes.
problem Realistic image and video manipulation threats, especially deepfakes.
method Semi-fragile watermarking using neural networks, robust to face-swapping but fragile to deepfake manipulations.
result FaceSigns can reliably detect deepfake content with high accuracy.
Quantum physics model uses knot theory for fragile topology.
problem Modeling quantum physics' fragile topology.
method Knot theoretic algorithm.
result Quantum physics' fragile topology modeled.
Transfer learning framework for fragility modeling under domain shift and class imbalance
problem Data gaps in structural fragility modeling
method Transfer learning
result Improves failure detection and predictive stability in low-data regimes
A framework for the generation of bridge-specific fragility utilizing the capabilities of machine learning and stripe-based approach is presented in this paper. The proposed methodology using random forests helps to generate or update fragility curves for a new set of input parameters with less computational effort and…
New research investigates why influence functions are fragile and proposes new validation procedures.
problem Understanding and mitigating the fragility of influence functions in deep learning model explanations.
method Verification of influence functions using various conditions and procedures, including convexity and non-convexity.
result Validation procedures may cause the observed fragility of influence functions.
BN helps learn fragile features, which can improve adversarial robustness.
problem The role of batch normalization in adversarial training and its impact on robustness.
method Investigated the expressiveness of BN in learning robust features compared to random features.
result Adversarially fine-tuning BN layers can result in non-trivial adversarial robustness.
The paper uses geometry to assess how hard examples are for NLP models.
problem Challenges in NLP datasets and classifiers, especially with shallow features.
method Information geometry to quantify example difficulty, exploring BERT, CNN, and fasttext.
result Deep learning models are vulnerable to word substitutions in difficult examples.
Measuring systemic risk or fragility of financial systems is a ubiquitous task of fundamental importance in analyzing market efficiency, portfolio allocation, and containment of financial contagions. Recent attempts have shown that representing such systems as a weighted graph characterizing the complex web of interact…
This study examines deep hedging for S&P 500 options, revealing systematic delta corrections and fragility.
problem Understanding and validating deep hedging strategies for financial options.
method Compared TD3 agents with a Black-Scholes delta hedge, using walk-forward tests and symbolic regression.
result Deep hedging agents learn systematic delta corrections, which can improve performance but are regime-fragile.
We provide a mathematical definition of fragility and antifragility as negative or positive sensitivity to a semi-measure of dispersion and volatility (a variant of negative or positive "vega") and examine the link to nonlinear effects. We integrate model error (and biases) into the fragile or antifragile context. Unli…
The 2008 financial crisis revealed banking consolidation paradoxically increased systemic fragility and global financial contagion with negligible spatial decay.
problem Fundamental vulnerabilities in interconnected banking systems during the 2008 financial crisis were inadequately addressed by existing frameworks.
method Developed a unified spatial-network framework using spectral analysis of network Laplacian operators combined with spatial difference-in-differences identification.
result Banking consolidation paradoxically increased systemic fragility and global financial contagion with negligible spatial decay.
Active learning method optimizes seismic fragility curve estimation.
problem Optimizing calls to complex numerical models for fragility curve estimation.
method Importance sampling based active learning for parametric seismic fragility curve estimation.
result The method optimizes the estimation of fragility curves with mathematical rigor.
Fragility curves which express the failure probability of a structure, or critical components, as function of a loading intensity measure are nowadays widely used (i) in Seismic Probabilistic Risk Assessment studies, (ii) to evaluate impact of construction details on the structural performance of installations under se…
AI systems that explain their decisions can be monitored for harmful intentions.
problem Monitoring AI systems' decision-making processes for harmful intentions is imperfect and can miss some misbehavior.
method Monitoring the chain of thought (CoT) of AI systems that communicate in human language.
result CoT monitoring is a promising but fragile approach to AI safety.
Study analyzes smart contract adoption under bounded risk, showing stable adoption but fragile financial outcomes.
problem Understanding smart contract adoption in derivative markets under risk constraints.
method Structural theory linked with simulation and real-world validation.
result Adoption intensity is stable but profitability and service outcomes are sensitive to volatility.
Research shows ESG signals lower exposure to market fragility during stress periods.
problem Market fragility often occurs together, and ESG is associated with reduced exposure.
method Monthly data on S&P 500 constituents from 2014 to 2025, analyzing downside returns, volatility, illiquidity, and cofragility states.
result A one-standard-deviation increase in ESG lowers the probability of severe cofragility by 0.92 percentage points during stress periods.
CoCos can increase financial fragility in certain network structures.
problem The effectiveness of CoCos in enhancing financial stability depends on the network structure.
method Analysis of phase transitions in a network of interconnected banks.
result CoCos can increase financial fragility under certain network structures.
We introduce a general framework for models of cascade and contagion processes on networks, to identify their commonalities and differences. In particular, models of social and financial cascades, as well as the fiber bundle model, the voter model, and models of epidemic spreading are recovered as special cases. To uni…
Study quantifies systemic risk in DeFi using network analysis.
problem Systemic risk in decentralized finance (DeFi) ecosystem.
method Network-based fragility analysis of TVL dynamics.
result Developed CFI and RCS to quantify structural fragility and risk contribution.
Study fragility in global financial indices using network analysis.
problem Monitor fragility in global financial indices.
method Network-based approach to analyze daily closing prices of global financial indices.
result Network-centric measures reveal fragility in global financial indices.
Adversarial attack methods have demonstrated the fragility of deep neural networks. Their imperceptible perturbations are frequently able fool classifiers into potentially dangerous misclassifications. We propose a novel way to interpret adversarial perturbations in terms of the effective input signal that classifiers …
Study on information cascade fragility under mismatched revealing probabilities.
problem Analyzing the fragility of information cascades in decision-making processes with imperfect knowledge of revealing probabilities.
method Examined sequential decision-making models with players having private information and imitating previous decisions. Studied the effect of a mismatch between players' beliefs and actual revealing probabilities.
result Derived closed-form expressions for optimal learning rates and identified phase transitions in the behavior of asymptotic learning rates.
Optimal Network Compressionq-fin.RM
Paper tackles optimal network compression for financial systems.
problem Optimal network compression for financial systems under shocks.
method Formulated as an NP-hard problem, studied systemic risk measures, and analyzed specific networks.
result Systemic fragility results no longer hold generally under shocks and heterogeneous networks.
In this paper we characterise the propensity of big capital investments to systematically deliver poor outcomes as "fragility," a notion suggested by Nassim Taleb. A thing or system that is easily harmed by randomness is fragile. We argue that, contrary to their appearance, big capital investments break easily - i.e. d…
Adversaries can manipulate cooperative MARL networks.
problem Fragility of consensus-based MARL algorithms to adversarial attacks.
method Study of adversarial attacks on consensus-based MARL networks.
result Consensus-based MARL algorithms are vulnerable to adversarial manipulation.
Deep networks are well-known to be fragile to adversarial attacks. We conduct an empirical analysis of deep representations under the state-of-the-art attack method called PGD, and find that the attack causes the internal representation to shift closer to the "false" class. Motivated by this observation, we propose to …
AI-driven investment strategies self-defeat at scale due to signal crowding and erosion.
problem Excess returns from AI-driven investment strategies diminish at scale due to signal crowding and erosion.
method Theoretical model and empirical validation using SEC Form 13F filings and hedge fund return dynamics.
result The alpha half-life of signals decreases significantly with AI adoption, leading to diminishing returns.
Measuring Strategy-Decay Risk: Minimum Regime Performance and the Durability of Systematic Investingq-fin.RM
Measures strategy durability through minimum regime performance, revealing trade-offs between efficiency and resilience.
problem Systematic investing strategies are vulnerable to regime changes, affecting their effectiveness and performance.
method Introduces minimum regime performance (MRP) to quantify the durability of systematic strategies, capturing how performance deteriorates under changing market conditions.
result Higher long-term Sharpe ratios do not always correlate with higher MRP, highlighting a new dimension of portfolio fragility.
Develops a framework for analyzing multi-agent and many-body systems with feedback loops.
problem Optimal order of multi-agent and general many-body systems
method Derive macroscopic properties and optimal degree of order
result Optimal degree of order balances productivity, stability, and adaptability
Trade networks, across which countries distribute their products, are crucial components of the globalized world economy. Their structure is strongly heterogeneous across products, given the different features of the countries which buy and sell goods. By using a diversified pool of indicators from network science and …
New framework explains adversarial examples in neural nets.
problem Adversarial examples in deep neural networks are counterintuitive and hard to explain.
method Introduces Dimpled Manifold Model to explain training phases and adversarial examples.
result Shows how adversarial examples arise from training dynamics and dimpling phase.
High-Dimensional Interpolators Can Be Fragile: Heavy Tails and High-Dimensional Large Deviationsmath.ST
Interpolating models can have heavy-tailed risk, leading to rare but severe errors.
problem Interpolating models' tail risk is poorly understood, affecting rare but impactful errors.
method Large-deviation methods to study the fragility of high-dimensional linear interpolators.
result Ridgeless regression exhibits heavy-tailed risk, while ridge-regularized estimators have better tail behavior.
Hour-Aware Adaptive Risk Management for Autonomous Memecoin Trading
problem Autonomous memecoin trading system performance
method Hour-of-day effects, filter precision, fragility
result 40.5% win rate, mean per-trade return of +0.62%, cumulative +117.7%
Bitcoin fails to function as a stable currency or store of value.
problem Bitcoin's failure to serve as a reliable currency or store of value.
method Quantitative finance methods and economic arguments applied to cryptocurrencies.
result Bitcoin does not function as a currency, store of value, or inflation hedge.
IRM fails to capture natural invariances on simple problems.
problem IRM fails to capture natural invariances on simple problems.
method IRM formulation and practical linear variant.
result IRM can lead to worse generalization than unconstrained ERM.
Hidden cost: Smoothing shrinks decision boundaries, affecting class-wise accuracy.
problem The fragility of machine learning models and the need for robustness verification.
method Randomized smoothing approach to achieve statistical robustness.
result Smoothed classifiers' decision boundaries shrink, leading to class-wise accuracy disparity.
The MSPI predicts market stress with machine learning.
problem Estimating the probability of high market stress.
method L1-regularized logistic regression on stock fragility signals.
result MSPI tracks major stress episodes and improves accuracy.
Optimized bandit algorithms have heavy-tailed regret distributions that can grow faster than expected.
problem Heavy-tailed regret distributions in optimized bandit algorithms.
method Change-of-measure ideas and UCB algorithm modifications.
result Regret distributions of optimized UCB algorithms have a heavy Cauchy tail, and can grow faster than poly-logarithmically.
The weighted and directed network of countries based on the number of overseas banks is analyzed in terms of its fragility to the banking crisis of one country. We use two different models to describe transmission of shocks, one local and the other global. Depending on the original source of the crisis, the overall siz…
Study finds stock and crypto markets tend to be robust, not antifragile.
problem Understanding the resilience of financial markets to noise and disorder.
method Defined and tested a measure of antifragility for complex systems, analyzed stock and crypto market returns.
result Top performers in stock and crypto markets are robust, not antifragile.
The recent financial crisis have generated renewed interests in fragilities of global financial networks among economists and regulatory authorities. In particular, a potential vulnerability of the financial networks is the "financial contagion" process in which insolvencies of individual entities propagate through the…
The blockchain technology promises to transform finance, money and even governments. However, analyses of blockchain applicability and robustness typically focus on isolated systems whose actors contribute mainly by running the consensus algorithm. Here, we highlight the importance of considering trustless platforms wi…
We construct and study market models admitting optimal arbitrage. We say that a model admits optimal arbitrage if it is possible, in a zero-interest rate setting, starting with an initial wealth of 1 and using only positive portfolios, to superreplicate a constant c>1. The optimal arbitrage strategy is the strategy for…
CNNs overinterpret inputs, leading to high accuracy without meaningful features.
problem High accuracy in image classifiers can mask subtle model failures.
method Batched Gradient SIS method for discovering sufficient input subsets.
result Overinterpretation allows models to make confident predictions with masked input features.
FTX's failure linked to Terra-Luna collapse and Binance's influence.
problem FTX's collapse due to misuse of native token and reliance on leverage.
method Analyzed on-chain data, studied cryptocurrency dependency structures, and examined public trades.
result FTX's downfall was accelerated by Binance's tweets and public reaction.
When Alpha Disappears: A One-Switch Benchmark for Decision-Time Leakage in Financial Backtestsq-fin.RM
Benchmark detects decision-time leakage in financial backtests.
problem Detecting decision-time leakage in financial machine-learning backtests.
method Toggles one evaluation convention at a time around a clean -open reference, holding other factors fixed.
result Inflation is highly selective, affecting specific features and execution methods.